An evolutionary game decision-making method for lane changing of autonomous vehicles

Abstract

The present invention belongs to the technical field of lane-changing decision-making, and specifically relates to an evolutionary game decision-making method for lane-changing autonomous vehicles. The method comprises the following steps: during the process of the autonomous lane-changing vehicle changing from the current lane to the target lane, predicting the target vehicle of the autonomous lane-changing vehicle, collecting motion information of the autonomous lane-changing vehicle and the target vehicle in real time, and determining the lane-changing game scenario of the autonomous lane-changing vehicle; defining the autonomous lane-changing vehicle and the target vehicle as decision-making entities, determining the strategy set of the autonomous lane-changing vehicle and the target vehicle, and the strategy combination of the game between the two; constructing an evolutionary game model for the interactive decision-making of the autonomous lane-changing vehicle and the target vehicle; establishing a replicated dynamic equation for the decision-making entity; and formulating and executing a lane-changing decision based on the optimization results obtained from the evolutionary game model. The present invention enables the autonomous vehicle to adjust its lane-changing strategy in real time according to the traffic environment, thereby improving the performance of the human-machine co-driving system.

Description

Technical Field

[0001] The present invention belongs to the technical field of lane-changing decision-making, and in particular relates to an evolutionary game decision-making method for lane-changing of an autonomous driving vehicle. Background Art

[0002] With the advancement of technology, the development and widespread adoption of autonomous vehicles is expected to reduce traffic accidents, improve vehicle efficiency, ease traffic congestion, and reduce traffic emissions. The Society of Automotive Engineers categorizes autonomous driving technology into six levels: manual driving, assisted driving, partial driving, conditional driving, highly automated driving, and fully automated driving. Currently, autonomous driving technology is at the stage where partial and conditional driving are mature, and highly automated driving is beginning testing. Despite numerous breakthroughs in autonomous driving technology, due to the immaturity of the technology and incomplete laws and regulations, the road traffic system will inevitably have a coexistence of manually driven vehicles and vehicles of varying levels of automated driving before fully automated driving can be achieved.

[0003] Autonomous driving technology primarily consists of three components: information perception, decision-making planning, and control execution. Decision-making planning is key to ensuring that autonomous vehicles can accurately and smoothly complete various driving tasks. Lane changing is a crucial decision for autonomous vehicles. Existing research has proposed various autonomous driving lane-changing decision-making methods based on logic rules, machine learning, and game theory, but these methods all have shortcomings. Logic-based lane-changing decision-making methods rely on predefined, logically related rules, lack sufficient flexibility, and are difficult to adapt to complex traffic environments. Machine learning can learn driving behavior from driving behavior data, but it relies on large amounts of high-quality training data and has limited generalization capabilities for unknown situations.

[0004] Classical game theory can account for interactive decision-making between vehicles, but due to the limited number of one-off or limited rounds of games, the decision-making process lacks real-time and adaptability. Existing research on lane-changing decisions for autonomous vehicles based on evolutionary games has mostly considered safety, efficiency, and comfort when describing vehicle utility, but has neglected driver fatigue and the energy efficiency of autonomous vehicles, resulting in inconsistent and inappropriate evolutionary game results. Summary of the Invention

[0005] In view of the above shortcomings in the existing technology, the purpose of the present invention is to provide an evolutionary game decision-making method for lane changing of autonomous vehicles, which integrates multiple utilities such as safety, efficiency, comfort, fatigue and energy saving, and enables the autonomous vehicle to adjust its lane changing strategy in real time according to the traffic environment, so as to improve the performance of the human-machine co-driving system.

[0006] To achieve the above objectives, the present invention provides an evolutionary game decision-making method for lane changing of an autonomous driving vehicle, comprising the following steps:

[0007] S1. When an autonomous vehicle changes lanes from its current lane to a target lane, predict the target vehicle of the autonomous vehicle, collect motion information of the autonomous vehicle and the target vehicle in real time through sensors, and determine the lane-changing game scenario of the autonomous vehicle;

[0008] S2. Define the autonomous lane-changing vehicle and the target vehicle as decision-making entities, determine the strategy set of the autonomous lane-changing vehicle and the target vehicle, and the strategy combination of the autonomous lane-changing vehicle and the target vehicle;

[0009] S3. Construct an evolutionary game model for the interactive decision-making between the autonomous lane-changing vehicle and the target vehicle, including the utility function and utility matrix of the autonomous lane-changing vehicle and the target vehicle;

[0010] S4. Establish a replication dynamic equation for the decision-making subject, simulate the decision-making subject's strategy selection process, and adjust its strategy selection according to the utility of each strategy;

[0011] S5. Based on the optimization results obtained from the evolutionary game model, a lane-changing decision is made and executed.

[0012] As a preferred solution of the present invention, in S1, the motion information includes position, speed, and acceleration.

[0013] As a preferred solution of the present invention, in S1, the game scenario is specifically:

[0014] On one-way roads with two lanes or more, if the utility a vehicle receives in its current lane is lower than that in its target lane, the vehicle will perform a lane-changing decision based on its own and surrounding vehicle status to determine whether to change to the target lane. The vehicle in the current lane is considered the lane-changing vehicle, and the vehicle behind it in the target lane is considered the target vehicle.

[0015] If the behavior decisions of the lane-changing vehicle and the target vehicle can be accurately predicted, no game occurs between the lane-changing vehicle and the target vehicle. Specifically, if the lane-changing vehicle has started to change lanes and occupies the target lane, the target vehicle can only give way while the lane-changing vehicle continues to complete the lane change. At this time, no game occurs between the lane-changing vehicle and the target vehicle. If the target vehicle has not reached the conflict zone, the lane-changing vehicle executes the lane change operation, and the target vehicle does not need to brake or slow down and drives normally. At this time, no game occurs between the lane-changing vehicle and the target vehicle. Except for these two situations, a game occurs between the lane-changing vehicle and the target vehicle.

[0016] Considering that the lane-changing vehicle is an autonomous vehicle and the target vehicle is a manually driven vehicle or an autonomous vehicle, the game scenarios of autonomous vehicle lane changing are divided into scenario 1 and scenario 2. Scenario 1: the autonomous lane-changing vehicle plays against the manually driven target vehicle, and scenario 2: the autonomous lane-changing vehicle plays against the autonomous target vehicle.

[0017] As a preferred solution of the present invention, in said S2, the strategy set of the automatic driving lane-changing vehicle is {A i |i=1,2}={change lane, do not change lane}, the target vehicle’s strategy set is {T j |j=1,2}={give way, don’t give way}; the strategy combination of the autonomous driving lane-changing vehicle and the target vehicle is {(A i ,T j )|i,j∈{1,2}}={(change lane, give way),(change lane, do not give way),(do not change lane, give way),(do not change lane, do not give way)}.

[0018] As a preferred embodiment of the present invention, in said S3, for , the utility function of the decision-making subject includes:

[0019] The safety utility functions of the autonomous lane-changing vehicle and the target vehicle are:

[0020] (1);

[0021] (2);

[0022] Where, 、 are the safety utilities of the autonomous lane-changing vehicle and the target vehicle, respectively; d is the distance between the autonomous lane-changing vehicle and the target vehicle; 、 are the speeds of the autonomous driving lane-changing vehicle and the target vehicle at time t, respectively; 、 Represent the logical operators "and" and "or" respectively;

[0023] The efficiency utility functions of the autonomous lane-changing vehicle and the target vehicle are:

[0024] (3);

[0025] (4);

[0026] Where, 、 are the efficiency utilities of the autonomous lane-changing vehicle and the target vehicle, respectively; The desired speeds of the lane-changing vehicle and the target vehicle for automated driving; 、 are the accelerations of the autonomous lane-changing vehicle and the target vehicle at time t, respectively;

[0027] The comfort utility functions of the autonomous lane-changing vehicle and the target vehicle are:

[0028] (5);

[0029] (6);

[0030] Where, 、 are the comfort utilities of the autonomous lane-changing vehicle and the target vehicle, respectively; 、 are the accelerations of the autonomous lane-changing vehicle and the target vehicle at time t+4f, respectively, and f is the duration of each frame; 、 are the maximum acceleration and maximum deceleration of the autonomous lane-changing vehicle and the target vehicle, respectively;

[0031] The fatigue utility function of manually driving the target vehicle is:

[0032] (7);

[0033] Where, Fatigue effect of manually driving the target vehicle; 、 are the accelerations of the manually driven target vehicle at time t and time t+4f, respectively;

[0034] The energy-saving utility functions of the autonomous lane-changing vehicle and the autonomous target vehicle are:

[0035] (8);

[0036] (9);

[0037] Where, 、 are the energy-saving utilities of the autonomous lane-changing vehicle and the autonomous target vehicle, respectively; and are the frontal area and mass of the autonomous lane-changing vehicle, respectively; and are the frontal area and mass of the autonomous driving target vehicle respectively; is the quality factor; is the road slope; is the air density; is the wind speed; g is the acceleration due to gravity; 、 、 are rolling resistance coefficient, wind resistance coefficient and internal friction resistance coefficient respectively;

[0038] Each utility function is normalized, and its normalized value is expressed as:

[0039] (10);

[0040] Where, is the kth utility value obtained by decision-maker N using G when the strategy combination is {i, j}; N = {ALV, TV}, where ALV and TV are the autonomous lane-changing vehicle and the target vehicle, respectively; G = {S, E, C, F, ES}, where S, E, C, F, and ES represent safety utility, efficiency utility, comfort utility, fatigue utility, and energy-saving utility, respectively; k = {1, 2, 3, …, K}, where K is the sample size of the utility values ​​obtained by the decision-maker;

[0041] make 、 、 Represent the total utility of the autonomous lane-changing vehicle, the total utility of the manually driven target vehicle, and the total utility of the autonomous target vehicle, respectively. Then:

[0042] (11);

[0043] (12);

[0044] (13).

[0045] As a preferred solution of the present invention, in S3, the utility matrix of the decision-making subject specifically includes:

[0046] The utility matrix of the autonomous lane-changing vehicle and the manually driven target vehicle. When the autonomous lane-changing vehicle chooses to change lanes and the manually driven target vehicle chooses to give way, the utility is When the autonomous lane-changing vehicle chooses to change lanes and the manually driven target vehicle chooses not to give way, the utility is When the autonomous lane-changing vehicle chooses not to change lanes and the manually driven target vehicle chooses to give way, the utility is When the autonomous lane-changing vehicle chooses not to change lanes and the manually driven target vehicle chooses not to give way, the utility is ;

[0047] The utility matrix of the autonomous lane-changing vehicle and the autonomous target vehicle is: when the autonomous lane-changing vehicle chooses to change lanes and the autonomous target vehicle chooses to give way, the utility is: When the autonomous lane-changing vehicle chooses to change lanes and the autonomous target vehicle chooses not to give way, the utility is When the autonomous lane-changing vehicle chooses not to change lanes and the autonomous target vehicle chooses to give way, the utility is When the autonomous lane-changing vehicle chooses not to change lanes and the autonomous target vehicle chooses not to give way, the utility is ;

[0048] The proportions of the autonomous lane-changing vehicle choosing the lane-changing strategy and the non-lane-changing strategy are recorded as p and 1-p respectively, and the proportions of the target vehicle choosing the yielding strategy and the non-yielding strategy are recorded as q and 1-q respectively.

[0049] As a preferred solution of the present invention, in S4, the replication dynamic equation of the decision-making subject includes:

[0050] Expected utility of lane-changing and non-lane-changing strategies for autonomous vehicles 、 They are:

[0051] (14);

[0052] (15);

[0053] Average expected utility of lane-changing and non-lane-changing strategies for autonomous vehicles for:

[0054] (16);

[0055] Replicated dynamic equations for lane-changing strategies of autonomous vehicles for:

[0056] (17);

[0057] Expected utility of manually driven target vehicles choosing between yielding and not yielding strategies 、 They are:

[0058] (18);

[0059] (19);

[0060] Average expected utility of manually driven target vehicles choosing the give-way strategy and the no-yield strategy for:

[0061] (20);

[0062] Replication dynamic equations for the yield strategy selected by manually driven target vehicles Expressed as:

[0063] (twenty one);

[0064] Expected utility of autonomous driving target vehicles choosing the give-way strategy and the no-yield strategy 、 They are:

[0065] (twenty two);

[0066] (twenty three);

[0067] Average expected utility of the autonomous driving target vehicle choosing the give-way strategy and the no-yield strategy for:

[0068] (twenty four);

[0069] Replication dynamic equations for the autonomous driving target vehicle's yield strategy for:

[0070] (25).

[0071] As a preferred solution of the present invention, for the replication dynamic equation of the decision-making subject, let When choosing the yielding strategy or the non-yielding strategy for the target vehicle, the utility of the lane-changing strategy and the non-lane-changing strategy for the autonomous lane-changing vehicle is different, that is, in scenarios 1 and 2, , ;

[0072] make When choosing a lane-changing strategy or a non-lane-changing strategy for an autonomous vehicle, the utility of the target vehicle choosing a yielding strategy or a non-yielding strategy is different, that is, in scenario 1, , In scene 2, , ;

[0073] Then Equation (17) is simplified to Equation (26), and Equations (21) and (25) are simplified to Equation (27):

[0074] (26);

[0075] (27);

[0076] Where, represent or .

[0077] As a preferred embodiment of the present invention, in S5, the solution of the replicated dynamic equation is the optimization result of the evolutionary game model, and a specific lane-changing decision is made based on the solution, including the equilibrium point and the stability of the equilibrium point, wherein:

[0078] For the equilibrium point, the differential equations composed of equations (26) and (27) about p and q are solved to obtain equation (28), which gives the five equilibrium points of the game between the autonomous driving lane-changing vehicle and the target vehicle, namely (0,0), (0,1), (1,0), (1,1) and :

[0079] (28);

[0080] The Jacobian matrix J in the game is:

[0081] (29);

[0082] Regarding the stability of the equilibrium point, whether the equilibrium point is a stable point, saddle point, center point or unstable point depends on the determinant and the sign of the trace of the Jacobian matrix; according to the Friedman method, the judgment criterion for the equilibrium point type is obtained. When the determinant of the Jacobian matrix is ​​greater than 0 and the trace is less than 0, the equilibrium point is a stable point, and the strategy selected by the decision-maker is an evolutionary stable strategy.

[0083] As a preferred solution of the present invention, the Jacobian matrix determinant and the sign of the trace of the evolutionary game of the automatic driving lane-changing vehicle lane-changing depend on 、 、 、 The positive and negative;

[0084] Based on the utility function and utility matrix, in scenario 1, The eight corresponding situations are as follows:

[0085] Scenario 1: 、 、 and , the stable point is (1,1);

[0086] Scenario 2: 、 、 and , the stable points are (0,0) and (1,1);

[0087] Scenario 3: , , and , the stable point is (0,1);

[0088] Scenario 4: 、 、 and , the stable point is (0,0);

[0089] Scenario 5: 、 、 and , no stable point;

[0090] Scenario 6: 、 、 and , the stable point is (0,0);

[0091] Scenario 7: 、 、 and , the stable point is (0,1);

[0092] Scenario 8: 、 、 and , the stable point is (0,0);

[0093] In scenario 2, and Always established, meeting conditions 1 to 4;

[0094] Assuming the initial values ​​of p and q to be 0-1, respectively, numerical simulations were used to obtain the game evolution results. Based on the stability analysis of the game equilibrium point, the evolutionary stable strategies of the game system include the following three combinations: (lane change, give way), (no lane change, no give way), and (no lane change, give way).

[0095] Since the strategy combination (changing lanes, not giving way) will bring safety risks to both decision-makers, the corresponding equilibrium point cannot be a stable point;

[0096] The autonomous lane-changing vehicle makes behavioral decisions based on the strategy corresponding to the evolutionary game results: first, it identifies the evolutionarily stable strategy; then, based on the current operating state, it determines whether the currently selected strategy is an evolutionarily stable strategy. If the currently selected strategy is an evolutionarily stable strategy, then the currently selected strategy is maintained; if the currently selected strategy is not an evolutionarily stable strategy, then the evolutionarily stable strategy is selected; if there are multiple evolutionarily stable strategies, then the strategy with the largest total utility is selected.

[0097] The algorithm involved in the present invention can be executed by an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The above-mentioned algorithm calculation is realized by executing the software through the processor.

[0098] The beneficial effects of the present invention are:

[0099] This invention integrates multiple utilities, including safety, efficiency, comfort, fatigue, and energy conservation, to construct an evolutionary game model for interactive decision-making between autonomous vehicles and target vehicles. This model uses replicated dynamic equations to simulate the decision-making process of the decision-making entity and solves the equilibrium point of the evolutionary game model. The stability of the equilibrium point is determined using the Friedman method, and an evolutionarily stable strategy is then determined. This helps autonomous vehicles adjust their lane-changing strategies in real time based on changes in the traffic environment. Through strategy optimization, this improves the safety and intelligence of lane-changing decisions, enabling them to better adapt to complex traffic environments.

[0100] The utility function for the lane-changing game of autonomous vehicles in this invention not only considers safety, efficiency, and comfort, but also fatigue and energy conservation. By factoring in fatigue utility, the lane-changing strategy of autonomous vehicles can be optimized by reducing driving errors caused by driver fatigue. By factoring in energy conservation utility, autonomous vehicles are encouraged to adopt low-energy and low-emission strategies, promoting environmental protection and sustainable development. This multi-utility integration provides a systematic lane-changing decision-making framework for autonomous vehicles, achieving a win-win situation in both economic and environmental benefits, and imbuing intelligent transportation systems with both intelligence and sustainability. BRIEF DESCRIPTION OF THE DRAWINGS

[0101] Figure 1 It is a schematic diagram of the process of the present invention;

[0102] Figure 2 Schematic diagram of a scenario in which an autonomous lane-changing vehicle and a target vehicle do not compete with each other in an embodiment of the present invention. Figure 2 (a) is a schematic diagram of an autonomous lane-changing vehicle occupying the target lane; Figure 2 (b) is a schematic diagram of the target vehicle not reaching the conflict zone;

[0103] Figure 3 2. Schematic diagram of a game scenario of an autonomous driving lane-changing vehicle in an embodiment of the present invention; Figure 3 (a) is a schematic diagram of scenario 1; Figure 3 (b) is a schematic diagram of scenario 2;

[0104] Figure 4 is a schematic diagram of a shooting scene during the verification process of the present invention;

[0105] Figure 5 is a schematic diagram of determining whether the target vehicle has reached the conflict zone during the verification process of the present invention;

[0106] Figure 6 It is an evolutionary path diagram of the game between the autonomous driving lane-changing vehicle and the target vehicle during the verification process of the present invention; Figure 6(a) in the figure is the evolution path diagram with the stable point (0,0); Figure 6 (b) in the figure is the evolution path diagram with the stable point (0,1); Figure 6 (c) in the figure is the evolution path diagram with the stable point (1,1); Figure 6 (d) in the figure is the evolution path diagram with stable points (0,0) and (1,1);

[0107] Figure 7 is an evolutionary path diagram of the lane change of the autonomous driving vehicle during the verification process of the present invention; Figure 7 (a) in the figure is the evolution path diagram of scenario 1; Figure 7 (b) in the figure is the evolution path diagram of scenario 2. DETAILED DESCRIPTION

[0108] The embodiments of the present invention are further described below with reference to the accompanying drawings:

[0109] like Figure 1 As shown, an evolutionary game decision-making method for lane changing of an autonomous driving vehicle includes the following steps:

[0110] S1. When an autonomous vehicle changes lanes from its current lane to a target lane, predict the target vehicle of the autonomous vehicle, collect motion information of the autonomous vehicle and the target vehicle in real time through sensors, and determine the lane-changing game scenario of the autonomous vehicle;

[0111] S2. Define the autonomous lane-changing vehicle and the target vehicle as decision-making entities, determine the strategy set of the autonomous lane-changing vehicle and the target vehicle, and the strategy combination of the autonomous lane-changing vehicle and the target vehicle;

[0112] S3. Construct an evolutionary game model for the interactive decision-making between the autonomous lane-changing vehicle and the target vehicle, including the utility function and utility matrix of the autonomous lane-changing vehicle and the target vehicle;

[0113] S4. Establish a replication dynamic equation for the decision-making subject, simulate the decision-making subject's strategy selection process, and adjust its strategy selection according to the utility of each strategy;

[0114] S5. Based on the optimization results obtained from the evolutionary game model, a lane-changing decision is made and executed.

[0115] Based on the above method, the lane change goal can be effectively achieved under the premise of safety. Motion information includes position, speed, and acceleration.

[0116] In S1, the specific game scenario is:

[0117] On one-way roads with two lanes or more, if the utility a vehicle receives in its current lane is lower than that in its target lane, the vehicle will perform a lane-changing decision based on its own and surrounding vehicle status to determine whether to change to the target lane. The vehicle in the current lane is considered the lane-changing vehicle, and the vehicle behind it in the target lane is considered the target vehicle.

[0118] If the behavioral decisions of the lane-changing vehicle and the target vehicle can be accurately predicted, no game will occur between the lane-changing vehicle and the target vehicle. Specifically, if the lane-changing vehicle has started to change lanes and occupies the target lane, the target vehicle can only give way while the lane-changing vehicle continues to complete the lane change. At this time, no game will occur between the lane-changing vehicle and the target vehicle. If the target vehicle has not reached the conflict zone (the target vehicle is quite far away from the lane-changing vehicle), the lane-changing vehicle performs the lane-changing operation, and the target vehicle does not need to brake or decelerate and drives normally. At this time, no game will occur between the lane-changing vehicle and the target vehicle. Except for these two situations, a game will occur between the lane-changing vehicle and the target vehicle.

[0119] Figure 2 It shows a scenario where the autonomous lane-changing vehicle and the target vehicle do not compete with each other. Figure 2 In (a), the autonomous lane-changing vehicle (ALV) has started to change lanes and occupies the target lane (TL). The target vehicle (TV) can only give way while the autonomous lane-changing vehicle continues to complete the lane change. At this time, there is no game between the autonomous lane-changing vehicle and the target vehicle. Figure 2 In (b), the target vehicle has not yet reached the conflict zone, the autonomous lane-changing vehicle executes the lane-changing maneuver, and the target vehicle drives normally without braking or decelerating. In this case, no negotiation occurs between the autonomous lane-changing vehicle and the target vehicle. Except for these two scenarios, negotiation occurs between the autonomous lane-changing vehicle and the target vehicle.

[0120] Considering that the lane-changing vehicle is an autonomous vehicle and the target vehicle is a manually driven vehicle or an autonomous vehicle, the game scenario of the autonomous vehicle lane-changing is divided into scenario 1 and scenario 2. Scenario 1: Figure 3 As shown in (a), the autonomous lane-changing vehicle competes with the manually driven target vehicle (HTV). Scenario 2: Figure 3 As shown in (b), the autonomous lane-changing vehicle competes with the autonomous target vehicle (ATV).

[0121] In S2, the strategy set of the autonomous lane-changing vehicle is {A i |i=1,2}={change lane, do not change lane}, the target vehicle’s strategy set is {T j |j=1,2}={give way, don’t give way}; the strategy combination of the autonomous driving lane-changing vehicle and the target vehicle is {(A i ,T j)|i,j∈{1,2}}={(change lane, give way),(change lane, do not give way),(do not change lane, give way),(do not change lane, do not give way)}.

[0122] In lane-changing decisions for autonomous vehicles, "utility" is a key concept used to quantify and evaluate the gains or losses of a vehicle under a specific strategy. The utility function is an important tool in the decision-making process, helping autonomous vehicles make optimal lane-changing decisions.

[0123] In S3, for , the utility function of the decision-making subject includes:

[0124] The safety utility functions of the autonomous lane-changing vehicle and the target vehicle are:

[0125] (1);

[0126] (2);

[0127] Where, 、 are the safety utilities of the autonomous lane-changing vehicle and the target vehicle, respectively; d is the distance between the autonomous lane-changing vehicle and the target vehicle; 、 are the speeds of the autonomous driving lane-changing vehicle and the target vehicle at time t, respectively; 、 Represent the logical operators "and" and "or" respectively;

[0128] The efficiency utility functions of the autonomous lane-changing vehicle and the target vehicle are:

[0129] (3);

[0130] (4);

[0131] Where, 、 are the efficiency utilities of the autonomous lane-changing vehicle and the target vehicle, respectively; The expected speeds of the lane-changing vehicle and the target vehicle (the expected speeds of both are the same); 、 are the accelerations of the autonomous lane-changing vehicle and the target vehicle at time t, respectively;

[0132] The comfort utility functions of the autonomous lane-changing vehicle and the target vehicle are:

[0133] (5);

[0134] (6);

[0135] Where, 、 are the comfort utilities of the autonomous lane-changing vehicle and the target vehicle, respectively; 、 are the accelerations of the autonomous lane-changing vehicle and the target vehicle at time t+4f, respectively, and f is the duration of each frame; 、 are the maximum acceleration and maximum deceleration of the autonomous lane-changing vehicle and the target vehicle, respectively;

[0136] The fatigue utility function of manually driving the target vehicle is:

[0137] (7);

[0138] Where, Fatigue effect of manually driving the target vehicle; 、 are the accelerations of the manually driven target vehicle at time t and time t+4f, respectively;

[0139] The energy-saving utility functions of the autonomous lane-changing vehicle and the autonomous target vehicle are:

[0140] (8);

[0141] (9);

[0142] Where, 、 are the energy-saving utilities of the autonomous lane-changing vehicle and the autonomous target vehicle, respectively; and are the frontal area and mass of the autonomous lane-changing vehicle, respectively; and are the frontal area and mass of the autonomous driving target vehicle respectively; is the quality factor; is the road slope; is the air density; is the wind speed; g is the acceleration due to gravity; 、 、 are rolling resistance coefficient, wind resistance coefficient and internal friction resistance coefficient respectively;

[0143] Since the dimensions of safety utility, efficiency utility, comfort utility, fatigue utility, and energy-saving utility are different and cannot be directly added, each utility function is normalized, and its normalized value is expressed as:

[0144] (10);

[0145] Where, is the kth utility value obtained by decision-maker N using G when the strategy combination is {i, j}; N = {ALV, TV}, where ALV and TV are the autonomous lane-changing vehicle and the target vehicle, respectively; G = {S, E, C, F, ES}, where S, E, C, F, and ES represent safety utility, efficiency utility, comfort utility, fatigue utility, and energy-saving utility, respectively; k = {1, 2, 3, …, K}, where K is the sample size of the utility values ​​obtained by the decision-maker;

[0146] make 、 、 Represent the total utility of the autonomous lane-changing vehicle, the total utility of the manually driven target vehicle, and the total utility of the autonomous target vehicle, respectively. Then:

[0147] (11);

[0148] (12);

[0149] (13).

[0150] The utility matrix of the decision-making subject specifically includes:

[0151] As shown in Table 1, the utility matrix of the autonomous lane-changing vehicle and the manually driven target vehicle is: when the autonomous lane-changing vehicle chooses to change lanes and the manually driven target vehicle chooses to give way, the utility is: When the autonomous lane-changing vehicle chooses to change lanes and the manually driven target vehicle chooses not to give way, the utility is When the autonomous lane-changing vehicle chooses not to change lanes and the manually driven target vehicle chooses to give way, the utility is When the autonomous lane-changing vehicle chooses not to change lanes and the manually driven target vehicle chooses not to give way, the utility is .

[0152] Table 1 Utility matrix of the autonomous lane-changing vehicle and the manually driven target vehicle

[0153]

[0154] That is, when i and j are both 1 , the rest are similar;

[0155] As shown in Table 2, the utility matrix of the autonomous lane-changing vehicle and the autonomous target vehicle is: when the autonomous lane-changing vehicle chooses to change lanes and the autonomous target vehicle chooses to give way, the utility is: When the autonomous lane-changing vehicle chooses to change lanes and the autonomous target vehicle chooses not to give way, the utility is When the autonomous lane-changing vehicle chooses not to change lanes and the autonomous target vehicle chooses to give way, the utility is When the autonomous lane-changing vehicle chooses not to change lanes and the autonomous target vehicle chooses not to give way, the utility is .

[0156] Table 2 Utility matrix of the autonomous lane-changing vehicle and the autonomous target vehicle

[0157]

[0158] The proportions of the autonomous lane-changing vehicle choosing the lane-changing strategy and the non-lane-changing strategy are recorded as p and 1-p respectively, and the proportions of the target vehicle choosing the yielding strategy and the non-yielding strategy are recorded as q and 1-q respectively.

[0159] In S4, the replication dynamic equations of the decision-making subject include:

[0160] Expected utility of lane-changing and non-lane-changing strategies for autonomous vehicles 、 They are:

[0161] (14);

[0162] (15);

[0163] Average expected utility of lane-changing and non-lane-changing strategies for autonomous vehicles for:

[0164] (16);

[0165] Replicated dynamic equations for lane-changing strategies of autonomous vehicles for:

[0166] (17);

[0167] Expected utility of manually driven target vehicles choosing between yielding and not yielding strategies 、 They are:

[0168] (18);

[0169] (19);

[0170] Average expected utility of manually driven target vehicles choosing the give-way strategy and the no-yield strategy for:

[0171] (20);

[0172] Replication dynamic equations for the yield strategy selected by manually driven target vehicles Expressed as:

[0173] (twenty one);

[0174] Expected utility of autonomous driving target vehicles choosing the give-way strategy and the no-yield strategy 、 They are:

[0175] (twenty two);

[0176] (twenty three);

[0177] Average expected utility of the autonomous driving target vehicle choosing the give-way strategy and the no-yield strategy for:

[0178] (twenty four);

[0179] Replication dynamic equations for the autonomous driving target vehicle's yield strategy for:

[0180] (25).

[0181] For the replication dynamic equation of the decision-making subject, let When choosing the yielding strategy or the non-yielding strategy for the target vehicle, the utility of the lane-changing strategy and the non-lane-changing strategy for the autonomous lane-changing vehicle is different, that is, in scenarios 1 and 2, , ;

[0182] make When choosing a lane-changing strategy or a non-lane-changing strategy for an autonomous vehicle, the utility of the target vehicle choosing a yielding strategy or a non-yielding strategy is different, that is, in scenario 1, , In scene 2, , ;

[0183] Then Equation (17) is simplified to Equation (26), and Equations (21) and (25) are simplified to Equation (27):

[0184] (26);

[0185] (27);

[0186] Where, represent or .

[0187] In S5, the solution of the replicated dynamic equation is the optimization result of the evolutionary game model, based on which the specific lane-changing decision is made, including the equilibrium point and the stability of the equilibrium point, where:

[0188] For the equilibrium point, the differential equations composed of equations (26) and (27) about p and q are solved to obtain equation (28), which gives the five equilibrium points of the game between the autonomous driving lane-changing vehicle and the target vehicle, namely (0,0), (0,1), (1,0), (1,1) and :

[0189] (28);

[0190] The Jacobian matrix J in the game is:

[0191] (29);

[0192] Regarding equilibrium stability, whether an equilibrium point is stable, a saddle point, a center point, or an unstable point depends on the determinant and the sign of the trace of the Jacobian matrix. The Friedman method provides the criteria for determining equilibrium type, as shown in Table 3. When the determinant of the Jacobian matrix is ​​greater than 0 and the trace is less than 0, the equilibrium point is stable, and the strategy selected by the decision-maker is an evolutionarily stable strategy.

[0193] Table 3 Criteria for determining the type of equilibrium point in evolutionary games

[0194]

[0195] Table 4 gives the determinant and trace of the Jacobian matrix of the evolutionary game of the autonomous driving lane-changing vehicle. It can be seen that the positive and negative of the determinant and trace of the Jacobian matrix of the evolutionary game of the autonomous driving lane-changing vehicle depends on 、 、 、 positive and negative.

[0196] Table 4 Evolutionary game equilibrium points and Jacobian matrix determinants and traces

[0197]

[0198] As shown in Table 5, based on the utility function and utility matrix, in scenario 1, The eight corresponding situations are as follows:

[0199] Scenario 1: 、 、 and , the stable point is (1,1);

[0200] Scenario 2: 、 、 and , the stable points are (0,0) and (1,1);

[0201] Scenario 3: , , and , the stable point is (0,1);

[0202] Scenario 4: 、 、 and , the stable point is (0,0);

[0203] Scenario 5: 、 、 and , no stable point;

[0204] Scenario 6: 、 、 and , the stable point is (0,0);

[0205] Scenario 7: 、 、 and , the stable point is (0,1);

[0206] Scenario 8: 、 、 and , the stable point is (0,0);

[0207] In scenario 2, and Always true, meets the conditions 1 to 4.

[0208] Table 5 Stability analysis of the equilibrium point of evolutionary game

[0209]

[0210] Assuming the initial values ​​of p and q to be 0-1, respectively, numerical simulations were used to obtain the game evolution results. Based on the stability analysis of the game equilibrium point, the evolutionary stable strategies of the game system include the following three combinations: (lane change, give way), (no lane change, no give way), and (no lane change, give way).

[0211] Since the strategy combination (changing lanes, not giving way) will bring safety risks to both decision-makers, the corresponding equilibrium point cannot be a stable point;

[0212] The autonomous lane-changing vehicle makes behavioral decisions based on the strategy corresponding to the evolutionary game results: first, it identifies the evolutionarily stable strategy; then, based on the current operating state, it determines whether the currently selected strategy is an evolutionarily stable strategy. If the currently selected strategy is an evolutionarily stable strategy, then the currently selected strategy is maintained; if the currently selected strategy is not an evolutionarily stable strategy, then the evolutionarily stable strategy is selected; if there are multiple evolutionarily stable strategies, then the strategy with the largest total utility is selected.

[0213] The verification process is to use a DJI Mavic 2 Zoom drone to shoot the traffic flow in a certain expressway merging area, record the vehicle entry and exit conditions, driving trajectories, and road traffic environment information. Figure 4 Shows the scene shot by drone. Figure 4 In this scenario, the main road is a six-lane, two-way road. The vehicle in the current lane (ramp) is an autonomous vehicle changing lanes, and the rightmost lane of the main road is the target lane. A lane-changing decision strategy for the autonomous vehicle changing lanes in this scenario must be implemented. Tracker software is used to extract data from the video, obtaining the speed, acceleration, and position (x, y) coordinates of the autonomous vehicle changing lanes and the target vehicle, and storing them in a database.

[0214] Extract data from the database that matches the game between the autonomous lane-changing vehicle and the target vehicle. If the autonomous lane-changing vehicle does not occupy the target lane and the target vehicle reaches the conflict zone, there is a game between the two. The judgment conditions are:

[0215] (30);

[0216] (31);

[0217] Where, The longitudinal coordinate of the vehicle for autonomous lane change; is the longitudinal coordinate of the centerline of the target lane.

[0218] Among them, the three-second rule is used to determine whether the target vehicle has reached the conflict zone, such as Figure 5 shown. Figure 5 In the example, assume that at time t, the autonomous lane-changing vehicle is at point A and the target vehicle is at point B. If the target vehicle reaches point A within 3 seconds, the target vehicle needs to brake and decelerate to avoid colliding with the autonomous lane-changing vehicle. That is, the lane-changing behavior of the autonomous lane-changing vehicle affects the driving of the target vehicle, and the target vehicle reaches the conflict zone.

[0219] The acquired data is used to calculate the utility of the autonomous lane-changing vehicle and the target vehicle according to equations (1) to (13), and the statistical results of different types of utility are obtained, as shown in Table 6.

[0220] Table 6 Statistical results of different types of utility

[0221]

[0222] In Table 6, the average, maximum, and minimum values ​​of safety utility and efficiency utility are all in seconds; the average, maximum, and minimum values ​​of fatigue utility are all in meters per second cubed; and the average, maximum, and minimum values ​​of energy-saving utility are all in kilowatts per kilogram.

[0223] The utility matrix of the decision-making subject is calculated. Table 7 shows the utility matrix of the autonomous lane-changing vehicle and the manually driven target vehicle, and Table 8 shows the utility matrix of the autonomous lane-changing vehicle and the autonomous target vehicle.

[0224] Table 7 Utility matrix of autonomous lane-changing vehicles and manually driven target vehicles

[0225]

[0226] Table 8 Utility matrix of autonomous driving lane-changing vehicles and autonomous driving target vehicles

[0227]

[0228] The replicated dynamic equations for the autonomous lane-changing vehicle, the manually driven target vehicle, and the autonomous target vehicle are:

[0229] (32);

[0230] (33);

[0231] (34);

[0232] The evolutionary game model is solved, and specific lane-changing decisions are made based on the results to ensure that the lane-changing goal is effectively achieved while maintaining safety. Equation (28) allows us to obtain the five equilibrium points in the game between the autonomous vehicle and the target vehicle. In scenario 1, the five equilibrium points are (0, 0), (0, 1), (1, 0), (1, 1), and (0.8099, 0.8744); in scenario 2, the five equilibrium points are (0, 0), (0, 1), (1, 0), (1, 1), and (0.7166, 0.8744).

[0233] The Jacobian matrices J1 and J2 of the game systems in scenario 1 and scenario 2 are:

[0234] (35);

[0235] (36);

[0236] Table 9 lists the determinants and traces of the five equilibrium points corresponding to scenarios 1 and 2. Based on the determination of the equilibrium point type in Table 3, it is concluded that the stable point of the game system is (0,0) or (1,1). Figure 6 The evolution path of the game between the autonomous driving lane-changing vehicle and the target vehicle is shown. Scenario 1 and Scenario 2 are consistent with Figure 6 The evolution path in (d) is consistent with the second case in Table 5.

[0237] Table 9 Determinant and trace of equilibrium point

[0238]

[0239] The autonomous lane-changing vehicle makes behavioral decisions based on the strategy corresponding to the evolutionary game results. The vehicle's current operating state meets 、 、 If the game system is at equilibrium (0,0) or (1,1), meaning the decision-maker chooses the strategy combination (do not change lanes, do not yield) or (change lanes, yield), comparing the total utility of the two strategy combinations, the total utility of the strategy combination (do not change lanes, do not yield) is greater than the strategy combination (change lanes, yield), so the autonomous vehicle chooses not to change lanes. If the game system is not at equilibrium (0,0) or (1,1), the autonomous vehicle adjusts its current strategy to not change lanes. The game system guides the decision-maker's strategy choice to gradually evolve to the strategy combination (do not change lanes, do not yield).

[0240] Figure 7 The evolution path of the lane change of the autonomous driving vehicle corresponding to scenario 1 and scenario 2 is shown. Figure 7 As shown in the figure, the evolutionary path of the dynamic game exhibits distinct stage characteristics. When p and q are small, the game system is unstable, with large variations in p and q. The autonomous lane-changing vehicle and the target vehicle are constantly testing and adjusting their strategies. During the evolutionary process, the proportion of lane-changing or yielding strategies gradually decreases, ultimately converging to the strategy combination (no lane change, no yielding). When p and q are large, the game system gradually stabilizes, and the proportion of lane-changing or yielding strategies gradually increases, ultimately converging to the strategy combination (lane change, yielding).

[0241] Scenario 2 converged to a stable state more quickly than Scenario 1, indicating that the interactive decision-making between the autonomous lane-changing vehicle and the target vehicle was more efficient. Furthermore, the increased frequency of the strategy combination (lane change, yield) further demonstrates that in the game between autonomous vehicles, both parties are more likely to choose this strategy combination (lane change, yield). This demonstrates that when autonomous vehicles interact with each other, they tend to choose a cooperative strategy to achieve optimal overall utility.

[0242] In both Scenario 1 and Scenario 2, the evolutionary paths demonstrate the process of the vehicle continuously adjusting its strategy based on the utility function and the replication dynamic equation. The final strategy combination is consistent with the evolutionarily stable strategy analyzed in Table 5, further verifying the rationality and stability of the model in this example.

Claims

1. An evolutionary game decision-making method for lane changing of an autonomous vehicle, characterized by The following steps are involved: S1. When an autonomous vehicle changes lanes from its current lane to a target lane, predict the target vehicle of the autonomous vehicle, collect motion information of the autonomous vehicle and the target vehicle in real time through sensors, and determine the lane-changing game scenario of the autonomous vehicle; S2. Define the autonomous lane-changing vehicle and the target vehicle as decision-making entities, determine the strategy set of the autonomous lane-changing vehicle and the target vehicle, and the strategy combination of the autonomous lane-changing vehicle and the target vehicle; S3. Construct an evolutionary game model for the interactive decision-making between the autonomous lane-changing vehicle and the target vehicle, including the utility function and utility matrix of the autonomous lane-changing vehicle and the target vehicle; S4. Establish a replication dynamic equation for the decision-making subject, simulate the decision-making subject's strategy selection process, and adjust its strategy selection according to the utility of each strategy; S5. Based on the optimization results obtained from the evolutionary game model, a lane-changing decision is made and executed; In S2, the strategy set of the autonomous lane-changing vehicle is {A i |i=1,2}={change lane, do not change lane}, the target vehicle’s strategy set is {T j |j=1,2}={give way, don’t give way}; the strategy combination of the autonomous driving lane-changing vehicle and the target vehicle is {(A i ,T j )|i,j∈{1,2}}={(change lane, give way),(change lane, do not give way),(do not change lane, give way),(do not change lane, do not give way)}; In S3, for , the utility function of the decision-making subject includes: The safety utility functions of the autonomous lane-changing vehicle and the target vehicle are: （1）； （2）； Where, 、 are the safety utilities of the autonomous lane-changing vehicle and the target vehicle, respectively; d is the distance between the autonomous lane-changing vehicle and the target vehicle; 、 are the speeds of the autonomous driving lane-changing vehicle and the target vehicle at time t, respectively; 、 Represent the logical operators "and" and "or" respectively; The efficiency utility functions of the autonomous lane-changing vehicle and the target vehicle are: （3）； （4）； Where, 、 are the efficiency utilities of the autonomous lane-changing vehicle and the target vehicle, respectively; The desired speeds of the lane-changing vehicle and the target vehicle for automated driving; 、 are the accelerations of the autonomous lane-changing vehicle and the target vehicle at time t, respectively; The comfort utility functions of the autonomous lane-changing vehicle and the target vehicle are: （5）； （6）； Where, 、 are the comfort utilities of the autonomous lane-changing vehicle and the target vehicle, respectively; 、 are the accelerations of the autonomous lane-changing vehicle and the target vehicle at time t+4f, respectively, and f is the duration of each frame; 、 are the maximum acceleration and maximum deceleration of the autonomous lane-changing vehicle and the target vehicle, respectively; The fatigue utility function of manually driving the target vehicle is: （7）； Where, Fatigue effect of manually driving the target vehicle; 、 are the accelerations of the manually driven target vehicle at time t and time t+4f, respectively; The energy-saving utility functions of the autonomous lane-changing vehicle and the autonomous target vehicle are: （8）； （9）； Where, 、 are the energy-saving utilities of the autonomous lane-changing vehicle and the autonomous target vehicle, respectively; and are the frontal area and mass of the autonomous lane-changing vehicle, respectively; and are the frontal area and mass of the autonomous driving target vehicle respectively; is the quality factor; is the road slope; is the air density; is the wind speed; g is the acceleration due to gravity; 、 、 are rolling resistance coefficient, wind resistance coefficient and internal friction resistance coefficient respectively; Each utility function is normalized, and its normalized value is expressed as: （10）； Where, is the kth utility value obtained by decision-making subject N using G when the strategy combination is {i, j}; N = {ALV, TV}, where ALV and TV are the autonomous lane-changing vehicle and the target vehicle, respectively; G = {S, E, C, F, ES}, where S, E, C, F, and ES represent safety utility, efficiency utility, comfort utility, fatigue utility, and energy-saving utility, respectively; k = {1, 2, 3, …, K}, where K is the sample size of the utility value obtained by the decision-making subject; make 、 、 Represent the total utility of the autonomous lane-changing vehicle, the total utility of the manually driven target vehicle, and the total utility of the autonomous target vehicle, respectively. Then: （11）； （12）； （13）。 2. The evolutionary game decision-making method for lane changing of an autonomous driving vehicle according to claim 1, characterized in that: In the above-mentioned S1, the motion information includes position, speed, and acceleration.

3. The evolutionary game decision-making method for lane changing of an autonomous driving vehicle according to claim 1, characterized in that: In the aforementioned S1, the specific game scenario is: On one-way roads with two lanes or more, if the utility a vehicle receives in its current lane is lower than that in its target lane, the vehicle will perform a lane-changing decision based on its own and surrounding vehicle status to determine whether to change to the target lane. The vehicle in the current lane is considered the lane-changing vehicle, and the vehicle behind it in the target lane is considered the target vehicle. If the decisions of the lane-changing vehicle and the target vehicle can be accurately predicted, no negotiation occurs between them. Specifically, if the lane-changing vehicle has already started changing lanes and occupied the target lane, the target vehicle can only yield while the lane-changing vehicle continues to change lanes. In this case, no negotiation occurs between the lane-changing vehicle and the target vehicle. If the target vehicle has not reached the conflict zone, the lane-changing vehicle performs the lane-changing operation, and the target vehicle does not need to brake or slow down and drives normally. In this case, no game occurs between the lane-changing vehicle and the target vehicle. Except for these two cases, a game occurs between the lane-changing vehicle and the target vehicle. Considering that the lane-changing vehicle is an autonomous vehicle and the target vehicle is a manually driven vehicle or an autonomous vehicle, the game scenarios of autonomous vehicle lane changing are divided into scenario 1 and scenario 2. Scenario 1: the autonomous lane-changing vehicle plays against the manually driven target vehicle, and scenario 2: the autonomous lane-changing vehicle plays against the autonomous target vehicle.

4. The evolutionary game decision-making method for lane changing of an autonomous driving vehicle according to claim 3, characterized in that: In S3, the utility matrix of the decision-making subject specifically includes: The utility matrix of the autonomous lane-changing vehicle and the manually driven target vehicle. When the autonomous lane-changing vehicle chooses to change lanes and the manually driven target vehicle chooses to give way, the utility is When the autonomous lane-changing vehicle chooses to change lanes and the manually driven target vehicle chooses not to give way, the utility is When the autonomous lane-changing vehicle chooses not to change lanes and the manually driven target vehicle chooses to give way, the utility is When the autonomous lane-changing vehicle chooses not to change lanes and the manually driven target vehicle chooses not to give way, the utility is ; The utility matrix of the autonomous lane-changing vehicle and the autonomous target vehicle is: when the autonomous lane-changing vehicle chooses to change lanes and the autonomous target vehicle chooses to give way, the utility is: When the autonomous lane-changing vehicle chooses to change lanes and the autonomous target vehicle chooses not to give way, the utility is When the autonomous lane-changing vehicle chooses not to change lanes and the autonomous target vehicle chooses to give way, the utility is When the autonomous lane-changing vehicle chooses not to change lanes and the autonomous target vehicle chooses not to give way, the utility is ; The proportions of the autonomous lane-changing vehicle choosing the lane-changing strategy and the non-lane-changing strategy are recorded as p and 1-p respectively, and the proportions of the target vehicle choosing the yielding strategy and the non-yielding strategy are recorded as q and 1-q respectively.

5. The evolutionary game decision-making method for lane changing of an autonomous driving vehicle according to claim 4, characterized in that: In S4, the replication dynamic equation of the decision-making subject includes: Expected utility of lane-changing and non-lane-changing strategies for autonomous vehicles 、 They are: （14）； （15）； Average expected utility of lane-changing strategy and no lane-changing strategy for autonomous lane-changing vehicles for: （16）； Replicated dynamic equations for lane-changing strategies of autonomous vehicles for: （17）； Expected utility of manually driven target vehicles choosing between yielding and not yielding strategies 、 They are: （18）； （19）； Average expected utility of manually driven target vehicles choosing the give-way strategy and the no-give-way strategy for: （20）； Replication dynamic equations for the yield strategy selected by manually driven target vehicles Expressed as: （21）； Expected utility of autonomous driving target vehicles choosing the give-way strategy and the no-yield strategy 、 They are: （22）； （23）； Average expected utility of the autonomous driving target vehicle choosing the give-way strategy and the no-yield strategy for: （24）； Replication dynamic equations for the autonomous driving target vehicle's yield strategy for: （25）。 6. The evolutionary game decision-making method for lane changing of an autonomous driving vehicle according to claim 5, characterized in that: For the replication dynamic equation of the decision-making subject, let When choosing the yielding strategy or the non-yielding strategy for the target vehicle, the utility of the lane-changing strategy and the non-lane-changing strategy for the autonomous lane-changing vehicle is different, that is, in scenarios 1 and 2, , ; make When choosing a lane-changing strategy or a non-lane-changing strategy for an autonomous vehicle, the utility of the target vehicle choosing a yielding strategy or a non-yielding strategy is different, that is, in scenario 1, , In scene 2, , ; Then Equation (17) is simplified to Equation (26), and Equations (21) and (25) are simplified to Equation (27): （26）； （27）； Where, represent or .

7. The evolutionary game decision-making method for lane changing of an autonomous driving vehicle according to claim 6, characterized in that: In S5, the solution of the replicated dynamic equation is the optimization result of the evolutionary game model, based on which a specific lane-changing decision is made, including the equilibrium point and the stability of the equilibrium point, where: For the equilibrium point, the differential equations composed of equations (26) and (27) about p and q are solved to obtain equation (28), which gives the five equilibrium points of the game between the autonomous driving lane-changing vehicle and the target vehicle, namely (0,0), (0,1), (1,0), (1,1) and : （28）； The Jacobian matrix J in the game is: （29）； Regarding the stability of the equilibrium point, whether the equilibrium point is a stable point, saddle point, center point or unstable point depends on the determinant and the sign of the trace of the Jacobian matrix; according to the Friedman method, the judgment criterion for the equilibrium point type is obtained. When the determinant of the Jacobian matrix is ​​greater than 0 and the trace is less than 0, the equilibrium point is a stable point, and the strategy selected by the decision-maker is an evolutionary stable strategy.

8. The evolutionary game decision-making method for lane changing of an autonomous driving vehicle according to claim 7, characterized in that: The Jacobian matrix determinant and trace of the evolutionary game of lane-changing autonomous vehicles depend on the sign of 、 、 、 The positive and negative; Based on the utility function and utility matrix, in scenario 1, The eight corresponding situations are as follows: Scenario 1: 、 、 and , the stable point is (1,1); Scenario 2: 、 、 and , the stable points are (0,0) and (1,1); Scenario 3: , , and , the stable point is (0,1); Scenario 4: 、 、 and , the stable point is (0,0); Scenario 5: 、 、 and , no stable point; Scenario 6: 、 、 and , the stable point is (0,0); Scenario 7: 、 、 and , the stable point is (0,1); Scenario 8: 、 、 and , the stable point is (0,0); In scenario 2, and Always established, meeting conditions 1 to 4; Assuming the initial values ​​of p and q to be 0-1, respectively, numerical simulations were used to obtain the game evolution results. Based on the stability analysis of the game equilibrium point, the evolutionary stable strategies of the game system include the following three combinations: (lane change, give way), (no lane change, no give way), and (no lane change, give way). Since the strategy combination (changing lanes, not giving way) will bring safety risks to both decision-makers, the corresponding equilibrium point cannot be a stable point; The autonomous lane-changing vehicle makes behavioral decisions based on the strategy corresponding to the evolutionary game results: first, it identifies an evolutionarily stable strategy; then, based on the current operating state, it determines whether the currently selected strategy is an evolutionarily stable strategy. If so, it maintains the currently selected strategy. If the currently selected strategy is not an evolutionary stable strategy, then select an evolutionary stable strategy; if there are multiple evolutionary stable strategies, then select the strategy with the largest total utility.

Images