Vehicle lane changing method, device, electronic device and readable storage medium

Abstract

The present application relates to the field of autonomous driving technology and provides a vehicle lane change method, device, electronic device, and readable storage medium. The method includes: determining the lane change conflict position corresponding to each adjacent lane of the own vehicle in all adjacent lanes when determining that the own vehicle has an intention to change lanes; determining the target lane from each adjacent lane based on the lane change conflict position corresponding to each adjacent lane; determining the safety and comfort levels corresponding to the own vehicle and the target vehicle when different driving strategies are adopted within each preset time period; determining the target driving strategies of the own vehicle and the target vehicle based on the safety and comfort levels, and controlling the own vehicle to drive according to the corresponding target driving strategies within the preset time period until the own vehicle or the target vehicle passes the lane change conflict position. By comprehensively considering the traffic flow in the current lane, the target lane, and the non-target lanes, the own vehicle can make the optimal decision based on the global traffic status.

Description

Technical Field

[0001] The present application relates to the field of vehicle driving technology, and in particular to a vehicle lane changing method, device, electronic device, and readable storage medium. Background Art

[0002] With the continuous development of autonomous driving technology, the lane changing process in autonomous driving or intelligent assisted driving has received more attention. Automatic lane changing requires the vehicle to autonomously select the driving lane on the road and perform lane change operations. Appropriate lane changing decisions can better complete driving tasks, avoid traffic congestion, improve traffic efficiency, avoid traffic accidents, and ensure road safety.

[0003] Traditional smart car lane-changing algorithms may be applicable under simple traffic conditions, but they are insufficient in multi-lane or complex traffic environments. They are unable to cope with complex traffic conditions in real scenarios and cannot effectively avoid traffic bottlenecks and congestion. Summary of the Invention

[0004] In view of this, the embodiments of the present application provide a vehicle lane changing method, device, electronic device and readable storage medium to solve the problem in the prior art that vehicle lane changing is difficult to cope with complex traffic conditions in real scenarios and cannot effectively avoid traffic congestion.

[0005] In a first aspect of the present application, a vehicle lane changing method is provided, comprising:

[0006] When it is determined that the ego vehicle intends to change lanes, the lane change conflict position corresponding to each adjacent lane of the ego vehicle is determined. The lane change conflict position is the intersection point between the ego vehicle and the lane line passed by during the lane change process.

[0007] Determine the target lane from each adjacent lane based on the lane change conflict position corresponding to each adjacent lane;

[0008] Determine the safety and comfort levels for the ego vehicle and a target vehicle using different driving strategies within each preset time period. The target vehicle is the vehicle behind the ego vehicle in the target lane with the smallest distance to the ego vehicle. Driving strategies include acceleration, deceleration, and constant speed driving.

[0009] Based on safety and comfort, the target driving strategies corresponding to the own vehicle and the target vehicle within each preset time period are determined, and the own vehicle is controlled to drive with the corresponding target driving strategies within the preset time period until either the own vehicle or the target vehicle passes the lane change conflict position corresponding to the target lane.

[0010] In a second aspect of the present application, a vehicle lane changing device is provided, comprising:

[0011] a conflict position determination module configured to, upon determining that the ego vehicle intends to change lanes, determine a lane change conflict position corresponding to each adjacent lane of the ego vehicle, wherein the lane change conflict position is an intersection point between the ego vehicle and the lane line passed by the ego vehicle during the lane change process;

[0012] a lane determination module configured to determine a target lane from each adjacent lane based on a lane change conflict position corresponding to each adjacent lane;

[0013] a benefit determination module configured to determine the safety and comfort levels corresponding to different driving strategies adopted by the ego vehicle and a target vehicle within each preset time period, wherein the target vehicle is the vehicle located to the side and rear of the ego vehicle in the target lane and with the smallest distance from the ego vehicle, and the driving strategies include accelerating, decelerating, and driving at a constant speed;

[0014] The lane change control module is configured to determine the target driving strategies corresponding to the own vehicle and the target vehicle within each preset time period based on safety and comfort, and control the own vehicle to drive with the corresponding target driving strategies within the preset time period until either the own vehicle or the target vehicle passes the lane change conflict position corresponding to the target lane.

[0015] In a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0016] In a fourth aspect of the present application, a readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0017] Compared with the prior art, the beneficial effects of the embodiments of the present application are as follows: when it is determined that the own vehicle has the intention to change lanes, the intersection points of the own vehicle with each adjacent lane line during the lane change process, that is, the lane change conflict position corresponding to each adjacent lane in all adjacent lanes of the own vehicle, are calculated; according to the lane change conflict position corresponding to each adjacent lane, the target lane is determined from each adjacent lane; the safety and comfort corresponding to the own vehicle and the target vehicle when adopting different driving strategies within each preset time period are determined, and based on the safety and comfort, the target driving strategies corresponding to the own vehicle and the target vehicle within each preset time period are determined, and the own vehicle is controlled to drive with the corresponding target driving strategies within the preset time period until any of the own vehicle and the target vehicle passes the lane change conflict position corresponding to the target lane. The present application determines the lane change conflict position corresponding to each adjacent lane of all adjacent lanes of the own vehicle, comprehensively considering the traffic flow of all lanes in the current traffic scene, so that the own vehicle can make the optimal decision according to the global traffic status and with reference to comfort and safety, effectively avoiding traffic congestion during the lane change process, thereby improving overall traffic efficiency, and solving the problem that the vehicle lane change method in the existing technology only considers the game between the own vehicle and the vehicle in the target lane, is difficult to cope with the complex traffic conditions in real scenes, and cannot effectively avoid traffic congestion. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 This is a flow chart of a vehicle lane changing method provided in an embodiment of the present application;

[0020] Figure 2 This is a schematic diagram of a vehicle driving scenario in an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of a lane change conflict position in an embodiment of the present application;

[0022] Figure 4 1 is a schematic structural diagram of a vehicle lane changing device provided in an embodiment of the present application;

[0023] Figure 5 This is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0025] Traditional lane-changing algorithms for intelligent vehicles are often designed for dual-lane, urban roads, and only consider the interaction between the vehicle itself and the vehicle in the lane it is changing to, ignoring the impact of vehicles in other lanes. This limited consideration of local traffic flow information makes it difficult to accurately reflect complex traffic interactions in practical applications, especially in multi-lane and high-density traffic conditions. Consequently, these algorithms struggle to cope with complex real-world traffic conditions and are unable to effectively avoid bottlenecks and congestion.

[0026] In response to the above problems, the solution provided by the present application evaluates the lane change safety of different lanes by calculating the lane change conflict positions corresponding to each adjacent lane, and selects the safest target lane from them. It not only pays attention to the current lane and the target lane, but also considers the information of all adjacent lanes, thereby improving the flexibility and adaptability of lane change decisions, and making lane change decisions based on the global traffic status; after determining the target lane, the safety and comfort of the own vehicle and the target vehicle under different driving strategies are calculated, the safety and comfort of different strategies are evaluated, and the benefit values ​​of different strategies are calculated. According to the calculated safety and comfort corresponding to different driving strategies, the optimal driving strategy of the own vehicle and the target vehicle within each preset time length is determined, and the own vehicle is controlled to drive according to the determined optimal driving strategy until it passes the lane change conflict position, thereby allowing the vehicle to dynamically adjust the driving strategy according to the real-time traffic conditions, rather than a fixed strategy, thereby improving the flexibility and safety of the lane change process. This solution enables the vehicle itself to make the best decision based on the global traffic status, effectively avoiding traffic congestion during lane changes, thereby improving overall traffic efficiency and solving the problem that the existing technology only considers the game between the vehicle itself and the vehicle in the target lane when changing lanes, making it difficult to cope with complex traffic conditions in real scenarios and unable to effectively avoid traffic congestion. It also calculates the safety and comfort under different driving strategies, conducts game analysis in multiple dimensions, and by comprehensively considering safety and comfort, more intelligently selects the optimal driving strategy, thereby reducing the risk of traffic accidents and improving traffic flow and overall road utilization efficiency.

[0027] A method and device for changing lanes of a vehicle according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0028] Figure 1This is a flow chart of a vehicle lane changing method provided by an embodiment of the present application. Figure 1 As shown, the vehicle lane changing method includes:

[0029] Step 101, when it is determined that the own vehicle has an intention to change lanes, determine the lane change conflict position corresponding to each adjacent lane of all adjacent lanes of the own vehicle, where the lane change conflict position is the intersection of the own vehicle and the lane line passed during the lane change process.

[0030] Specifically, sensors and intelligent traffic systems can be used to obtain traffic information, including vehicle speed, lane status, etc., and use traffic information to determine whether the vehicle has the intention to change lanes.

[0031] The lane change conflict position is the potential conflict point between the ego vehicle's lane and the adjacent lane. This is the intersection of the ego vehicle's lane and the lane markings it passes through during the lane change process. The lane markings it passes through are the shared lane markings between the ego vehicle's lane and the adjacent lane. For example, if the ego vehicle changes lanes from its lane to the left lane, the lane change conflict position is the intersection of the shared lane markings between the ego vehicle's lane and the left lane during the lane change process.

[0032] By determining the lane change conflict locations for each of the ego vehicle's adjacent lanes, the ego vehicle can assess the safety of lane changes in each adjacent lane, ensuring that subsequent lane changes are feasible in both time and space. Furthermore, determining the lane change conflict locations for each of the ego vehicle's adjacent lanes provides a basis for subsequent decision-making, helping the ego vehicle determine when, how, and to which lane to change.

[0033] In this way, by comprehensively considering the traffic conditions of all adjacent lanes, the vehicle can make decisions based on the global traffic status during the lane change process, rather than relying solely on local information, enabling a more comprehensive assessment of the safety and feasibility of various lane change decisions.

[0034] Step 102 : Determine a target lane from the adjacent lanes based on the lane change conflict positions corresponding to the adjacent lanes.

[0035] Specifically, since the lane change conflict position is the intersection of the own vehicle and the lane line passed during the lane change process, that is, the lane change conflict position can reflect the distance between the own vehicle and the lane change conflict position, as well as the distance between the vehicle in the adjacent lane corresponding to the lane line and the lane change conflict position, the safety of the own vehicle passing through the lane change conflict position can be evaluated through the lane change conflict position, so that through the lane change conflict positions corresponding to each adjacent lane, a lane with high safety can be selected from all adjacent lanes as the target lane to be changed.

[0036] In this way, the target lane to be changed is determined according to the lane change conflict positions corresponding to each adjacent lane, realizing lane selection based on the global traffic status, effectively reducing the risk of traffic accidents and ensuring the safety of lane changes.

[0037] Step 103 determines the safety and comfort levels corresponding to different driving strategies for the ego vehicle and the target vehicle within each preset time period, where the target vehicle is the vehicle located to the side and rear of the ego vehicle in the target lane and has the smallest distance from the ego vehicle. Driving strategies include accelerating, decelerating, and driving at a constant speed.

[0038] Specifically, after determining the target lane, the vehicle determines the current safety and comfort level based on the status information of both the vehicle and the target vehicle, and makes decisions among various driving strategies, including accelerating to overtake, driving at a constant speed, and decelerating to avoid. Decelerations corresponding to decelerations can include -3.0, -2.8, -2.6, -2.4, -2.2, and so on, up to -0.2. Accelerations during constant speed driving are zero, and accelerations corresponding to accelerations can include 3.0, 2.8, 2.6, 2.4, 2.2, and so on, up to 0.2, and are not specifically limited here.

[0039] Among them, the target vehicle is the vehicle located behind the own vehicle in the target lane and has the smallest distance from the own vehicle, that is, the vehicle in the target lane that is about to pass the lane change conflict position corresponding to the target lane and is closest to the lane change conflict position.

[0040] Specifically, the preset duration is calculated by pre-dividing the time between the ego vehicle and the target vehicle before they pass through the lane change conflict position corresponding to the target lane. Each preset duration represents a single negotiation period between the ego vehicle and the target vehicle. As an example, the preset duration can be set to 1 second, 2 seconds, etc., and this is not limited here. However, to increase decision-making accuracy, the preset duration can be set to a smaller value, while to reduce decision-making workload, the preset duration can be set to a larger value.

[0041] Safety refers to a vehicle's ability to avoid collisions or other dangerous situations under a given driving strategy. It indicates the safety levels corresponding to different driving strategies adopted by the ego vehicle and the target vehicle. Specifically, the smaller the time difference between the ego vehicle and the target vehicle reaching the lane change conflict position at their respective speeds, the smaller the corresponding safety level. Safety includes the safety level corresponding to the ego vehicle and the target vehicle when the ego vehicle selects any of the driving strategies of acceleration, deceleration, and constant speed, and when the target vehicle selects any of the driving strategies of acceleration, deceleration, and constant speed. To illustrate this, the safety level includes the safety level corresponding to when the ego vehicle selects acceleration and the target vehicle selects acceleration, the safety level corresponding to when the ego vehicle selects acceleration and the target vehicle selects deceleration, and the safety level corresponding to when the ego vehicle selects acceleration and the target vehicle selects constant speed.

[0042] Comfort is used to indicate the comfort levels corresponding to different driving strategies for the ego vehicle and the target vehicle. It measures the smoothness of the vehicle during driving. The greater the degree of change in acceleration and deceleration, the worse the comfort and the lower the corresponding comfort level. Comfort includes the comfort level corresponding to the ego vehicle when it selects any of the driving strategies of acceleration, deceleration, and constant speed driving, and the comfort level corresponding to the target vehicle when it selects any of the driving strategies of acceleration, deceleration, and constant speed driving. To illustrate this, the comfort level includes the comfort level corresponding to the ego vehicle when it selects acceleration, the comfort level corresponding to the ego vehicle when it selects constant speed driving, the comfort level corresponding to the ego vehicle when it selects deceleration, the comfort level corresponding to the target vehicle when it selects deceleration, the comfort level corresponding to the target vehicle when it selects acceleration, and the comfort level corresponding to the target vehicle when it selects constant speed driving.

[0043] By calculating the safety level under different driving strategies, the potential risks of each driving strategy can be assessed, which helps to select the strategy with the lowest risk for execution. By calculating the comfort level under different driving strategies, it can be ensured that the vehicle does not cause excessive acceleration or deceleration changes during lane changes. The riding experience of each driving strategy can be evaluated, and the speed of the vehicle can be smoothly changed based on this indicator. By combining safety and comfort, the vehicle can more intelligently select the optimal driving strategy to cope with complex traffic conditions.

[0044] Step 104, based on the safety and comfort levels, determines the target driving strategies corresponding to the own vehicle and the target vehicle within each preset time period, and controls the own vehicle to drive according to the corresponding target driving strategies within the preset time period until either the own vehicle or the target vehicle passes the lane change conflict position corresponding to the target lane.

[0045] Specifically, each game cycle corresponding to a preset duration is considered a game round. Before either the ego vehicle or the target vehicle passes the lane change conflict position corresponding to the target lane, the entire lane change process can be considered a repeated game consisting of multiple rounds. In each round, different driving strategy combinations are evaluated from the perspectives of traffic safety (safety) and traffic comfort (comfort), and the optimal driving strategy is selected to form a Nash equilibrium. After the first decision is made, the ego vehicle makes a second decision based on the driving status of the other vehicle and its own. This process repeats until one vehicle successfully passes the lane change conflict position, at which point the conflict ends.

[0046] According to the technical solution provided in the embodiment of the present application, the target lane to be changed is first determined, and then based on safety and comfort, the target driving strategy is determined in each game round corresponding to a preset duration, thereby realizing lane change decision analysis for multi-lane and multi-vehicle intersection scenarios, so that vehicles can make optimal decisions based on global traffic conditions and individual preferences, effectively avoiding traffic bottlenecks and congestion during lane changing, and having certain adaptability and flexibility, and can dynamically adjust the decision-making strategy according to the real-time traffic conditions, vehicle status and vehicle preferences of different traffic scenarios, so as to maintain optimal traffic fluidity and road utilization.

[0047] In some embodiments, determining that the vehicle intends to change lanes includes:

[0048] Obtaining a first distance between the own vehicle and a first vehicle and a travel speed of the first vehicle, where the first vehicle is an adjacent vehicle located in front of the own vehicle in the lane where the own vehicle is located;

[0049] determining a distance difference between a first distance and a second distance, the second distance being a product of a travel speed of the first vehicle and a preset coefficient;

[0050] When the distance difference is greater than a preset distance, it is determined that the vehicle has an intention to change lanes.

[0051] Specifically, the first vehicle is in the same lane as the own vehicle and is the first vehicle before the own vehicle. Figure 2 As shown, assuming that the lanes include lane 1, lane 2 and lane 3, the vehicle CAV ego and vehicle CAR F2 Driving in lane 2, vehicle CAR R1 and vehicle CAR F1 Driving in lane 1, vehicle CAR R3 and vehicle CAR F3 Driving in lane 3, assuming the vehicle is a CAV ego , then the vehicle CAR D2 For the first vehicle.

[0052] The first distance is specifically the distance between the front of the own vehicle and the rear of the first vehicle, which can be measured by on-board sensors (such as radar, lidar or camera), and the driving speed of the first vehicle can be obtained by on-board sensors or vehicle communication systems (such as vehicle networking).

[0053] The first distance and the speed of the first vehicle are basic information for determining whether the vehicle needs to change lanes. Knowing the distance between the vehicle and the vehicle ahead and the speed of the vehicle ahead helps to assess the safety and traffic efficiency of the current lane.

[0054] The second distance is calculated by multiplying the first vehicle's speed by a preset coefficient. The preset coefficient can be an empirical value or a value set according to safety standards. The unit of the preset coefficient can be time units, which converts the speed into the distance the first vehicle can travel within the time corresponding to the preset coefficient. The greater the first vehicle's speed, the greater the distance it can travel within the time corresponding to the preset coefficient, and the higher the tolerance of the ego vehicle for the current lane, making a lane change less necessary. The lower the first vehicle's speed, the smaller the distance it can travel within the time corresponding to the preset coefficient, and the lower the tolerance of the ego vehicle for the current lane, making a lane change more necessary. Based on this, the difference between the first and second distances is calculated to assess whether the speed of the preceding vehicle is within an acceptable range. If the distance difference is greater than the preset distance, it indicates that the speed of the preceding vehicle is not within the acceptable range, and the ego vehicle intends to change lanes. The preset distance is a threshold set based on factors such as road conditions, traffic volume, and vehicle type.

[0055] Specifically, the above process of determining the lane change intention can be calculated by the following formula: r =L FV -v FV ·T s ;

[0056] Among them, L FV Indicates the first distance, v FV represents the speed of the first vehicle, T s Indicates the preset coefficient, which can be 2s. Assuming the preset distance is 6 meters, when F r When the value is greater than 6, the vehicle will have the intention to change lanes.

[0057] By acquiring and analyzing the distance between the own vehicle and the first vehicle and the speed information of the first vehicle in real time, it is determined whether the driving speed of the first vehicle in front of the own vehicle is within an acceptable range, thereby realizing the automatic determination process of the lane change intention.

[0058] In some embodiments, determining a lane change conflict position corresponding to each adjacent lane of all adjacent lanes of the ego vehicle includes:

[0059] Obtain the current location information and current driving speed of the vehicle;

[0060] Generates lane change trajectories for each adjacent lane based on the current position of the vehicle, the current speed of the vehicle, and the preset lane change completion time.

[0061] The intersection point of each lane change trajectory and the adjacent lane is determined as the lane change conflict position corresponding to the adjacent lane.

[0062] Specifically, the current position information of the own vehicle can be used to determine the exact position of the own vehicle on the road in order to plan the lane change path. The current driving speed of the own vehicle can affect the time required for lane change and the planning of the lane change path.

[0063] The lane change completion time is the time required for the vehicle to change lanes from its current position to the middle position in the other lane.

[0064] Based on the current position of the own vehicle, the current speed of the own vehicle, and the preset time required to complete the lane change, a cubic polynomial curve can be used to calculate and simulate possible lane change paths to generate the corresponding lane change trajectories when changing to each adjacent lane. The cubic polynomial curve is as follows:

[0065]

[0066] x(t) and y(t) are the longitudinal and lateral positions of the vehicle over time t; a k and b k are the cubic polynomial coefficients for the longitudinal and lateral positions, respectively; t0 is the time at which the vehicle begins its lane change. Based on cubic polynomial curve theory, determining the time required to complete a lane change can determine a unique lane change curve, thereby generating the corresponding lane change trajectory for each adjacent lane.

[0067] After determining the lane change trajectory, the intersection of each lane change trajectory and the adjacent lane can be determined as the lane change conflict location for the adjacent lane. Specifically, when determining the intersection of the lane change trajectory and the adjacent lane, a coordinate system can be established with the vehicle as the origin. The distance between the lane line corresponding to the adjacent lane and the vehicle's travel direction can be determined as the longitudinal displacement value. This longitudinal displacement value is then substituted into the lane change trajectory corresponding to the adjacent lane to determine the lateral displacement value. The point corresponding to the longitudinal and lateral displacement values ​​is then determined as the intersection point.

[0068] For example, as an example, Figure 3As shown, the vehicle CAV ego For example, when changing lanes from lane 2 to lane 1, after determining the lane change trajectory corresponding to lane 1, it can be seen that the lane change conflict location for lane 1 is the intersection point P of the lane change trajectory and lane 1. When calculating the coordinates of point P, the ordinate of point P can be pre-determined. Generally, the ordinate of point P is half the lane width, or 0.5D, where D is the lane width, typically 3.5 meters. 0.5D is then substituted into the lane change trajectory to obtain the abscissa L of point P. From this, the coordinates of point P are then determined, thereby determining the lane change conflict location for each of the ego vehicle's adjacent lanes.

[0069] In this way, this embodiment generates lane change trajectories corresponding to each adjacent lane by acquiring real-time vehicle data and determining potential lane change conflict locations, thereby effectively solving the limitations of traditional intelligent vehicle lane change algorithms in dealing with complex traffic conditions and improving the adaptability and safety of vehicles in real traffic environments.

[0070] In some embodiments, determining a target lane from each adjacent lane based on a lane change conflict position corresponding to each adjacent lane includes:

[0071] Determining a first conflict time for a second vehicle in each adjacent lane to reach the lane change conflict position, and determining a second conflict time for the own vehicle to reach the lane change conflict position; wherein the second vehicle is the vehicle in each adjacent lane that is located to the side and rear of the own vehicle and has the shortest distance from the own vehicle;

[0072] Determine the absolute value of the difference between the first conflict time and the second conflict time corresponding to each adjacent lane;

[0073] The adjacent lane corresponding to the largest absolute value among all absolute values ​​is determined as the target lane.

[0074] It should be noted that if Figure 2 As shown, the vehicle CAV ego Driving in lane 2, at this time for the own vehicle CAV ego There are three driving strategies: left lane change (changing to lane 1), right lane change (changing to lane 3), and following the vehicle in front (continuing in lane 2). ego and the car in front of the current lane, CAR F2 The game between the two, when it is determined that the own vehicle has the intention to change lanes, for the vehicle lane change behavior, taking the left lane change as an example, the own vehicle CAV ego CAR with the vehicle ahead F2 and the vehicle CAR in the adjacent lane F3 CAR F1 CAR R1 CAR R3Generate interaction, and in the actual traffic environment, the vehicle CAV ego The behavior of the vehicle in front has little impact on the vehicle in front, mainly the vehicle CAR in the adjacent lane located to the side and rear of the vehicle R1 CAR R3 CAV ego Therefore, in order to improve the calculation efficiency, this embodiment only considers the game between the own vehicle and the vehicle behind it in the adjacent lane for lane changing behavior.

[0075] Own vehicle CAV ego When the intention to change lanes is generated, the behavior decision is mainly related to the following vehicle. R1 The driving style of CAR is more aggressive, while R3 If the driving style is more conservative, then CAV ego More inclined to change lanes right; on the contrary, CAV ego If the driving style of the following vehicles is relatively aggressive, CAV ego More inclined to cancel lane change and continue driving in the original lane; if the driving style of the following vehicles is relatively conservative, then CAV ego A safer and more efficient lane will be selected as the target lane for lane change.

[0076] Based on the above principle, for each adjacent lane, the time it takes for the second vehicle in that lane to reach the lane change conflict position (first conflict time) and the time it takes for the own vehicle to reach the same conflict position (second conflict time) are calculated. The second vehicle is the vehicle in each adjacent lane that is located behind the own vehicle and has the smallest distance from the own vehicle. As an example, refer to Figure 2 , assuming the vehicle is a CAV in lane 2 ego , then in the adjacent lane 1 of the lane 1 where the vehicle is located, the second vehicle is CAR R1 , in the adjacent lane 3 of the own vehicle's lane 1, the second vehicle is CAR R3 .

[0077] In addition, when calculating the first conflict time and the second conflict time, the second vehicle CAR in each adjacent lane can be obtained through sensors, etc. R1 and CAR R3 The first conflict time T of the second vehicle arriving at the lane change conflict position corresponding to each adjacent lane is calculated based on the speed and position information of the second vehicle in each adjacent lane and the lane change conflict position corresponding to each adjacent lane. R , that is, vehicle CAR R1 The first conflict time T when arriving at the lane change conflict position corresponding to lane 1 R1 , and the vehicle CAR R3 The first conflict time T when arriving at the lane change conflict position corresponding to lane 3R3 According to CAV ego The speed, position information and lane change conflict positions corresponding to each adjacent lane (lane 1 and lane 3) are used to calculate the CAV ego The second conflict time T at which the lane change conflict position corresponding to each adjacent lane is reached ego ; Then calculate the absolute value of the difference between the first conflict time and the second conflict time corresponding to each adjacent lane, that is, Δt1=|T ego -T R1 |, Δt2=|T ego -T R3 |; The target lane is then determined as follows:

[0078]

[0079] That is, the absolute values ​​of the differences corresponding to all adjacent lanes are compared, and the adjacent lane corresponding to the largest absolute value is selected as the target lane. A larger absolute value of the time difference indicates that the possibility of the own vehicle and the second vehicle meeting at the same conflict position is smaller, thereby reducing the conflict risk during the lane change process.

[0080] By introducing the comparison of time differences, not only the traffic conditions of the current lane and the target lane are taken into account, but also the influence of other adjacent lanes. By comparing the time difference between vehicles in different lanes reaching the conflict position, the risk and safety of lane changes can be more comprehensively evaluated, thereby selecting the optimal lane, improving the vehicle's adaptability and decision-making ability in complex traffic environments.

[0081] In some embodiments, determining the safety levels corresponding to the ego vehicle and the target vehicle when using different driving strategies within each preset time period includes:

[0082] For the i-th preset duration, based on the first distance between the ego vehicle and the lane change conflict location at the beginning of the i-th preset duration and the ego vehicle's driving speed at the beginning of the i-th preset duration, determine the first time the ego vehicle reaches the lane change conflict location when using different driving strategies;

[0083] Determining, based on a second distance between the target vehicle and the lane change conflict position at the beginning of the i-th preset time period, a second time at which the target vehicle reaches the lane change conflict position when using different driving strategies;

[0084] Determine the absolute value of the time difference between the first time corresponding to any driving strategy and the second time corresponding to any driving strategy, and determine the absolute value of all time differences as the safety degree corresponding to different driving strategy combinations of the own vehicle and the target vehicle within the i-th preset time period, where the driving strategy combination is the driving strategy adopted by the own vehicle and the driving strategy adopted by the target vehicle, where i is greater than or equal to 1.

[0085] Specifically, the driving strategy combination includes the driving strategy of the own vehicle and the driving strategy of the target vehicle. For example, the driving strategy combination (3.0, -3.0) indicates that the driving strategy of the own vehicle within the preset time length is acceleration 3.0, and the driving strategy of the target vehicle within the preset time length is deceleration -3.0.

[0086] For each driving strategy combination corresponding to the ego vehicle and the target vehicle, at the i-th preset time, based on the first distance between the ego vehicle and the lane change conflict position at the beginning of the i-th preset time and the driving speed of the ego vehicle at the beginning of the i-th preset time, determine the first time for the ego vehicle to reach the lane change conflict position when using the ego vehicle driving strategy in the driving strategy combination.

[0087] For each driving strategy combination corresponding to the own vehicle and the target vehicle, at the i-th preset time length, according to the second distance between the target vehicle and the lane change conflict position at the beginning of the i-th preset time length and the driving speed of the target vehicle at the beginning of the i-th preset time length, the second time for the target vehicle to reach the lane change conflict position when adopting the target vehicle driving strategy in the driving strategy combination is determined.

[0088] Calculate the first time when the ego vehicle reaches the lane change conflict position when using the ego vehicle driving strategy in the driving strategy combination The second time when the target vehicle reaches the lane change conflict position when using the target vehicle's driving strategy The absolute value of And the absolute value of the time difference Determine the safety degree U corresponding to the driving strategy combination adopted by the own vehicle and the target vehicle within the i-th preset time length s ,Right now

[0089]

[0090] The larger the absolute value of the time difference, the greater the time difference between the two vehicles reaching the lane change conflict position, the smaller the possibility of conflict, and therefore the higher the safety level. Conversely, a smaller time difference indicates a higher encounter risk, that is, a lower safety level.

[0091] By determining the safety of the ego vehicle and the target vehicle when adopting different driving strategies within different preset time periods, the ego vehicle can more intelligently select the safest driving strategy during lane changes, thereby reducing the risk of traffic accidents.

[0092] In some embodiments, determining the comfort levels corresponding to the host vehicle and the target vehicle when using different driving strategies within each preset time period includes:

[0093] For any vehicle among the own vehicle and the target vehicle, determine the acceleration difference between the acceleration corresponding to the different driving strategies adopted by the vehicle at the i-th preset time length and the acceleration adopted at the i-1-th preset time length;

[0094] Determining the inverse of an acceleration ratio between the acceleration difference and a preset acceleration value, wherein the preset acceleration value is the difference between a maximum acceleration and a maximum deceleration that the vehicle can adopt;

[0095] The opposite of the acceleration ratio corresponding to the different driving strategies is determined as the comfort level corresponding to the different driving strategies of the vehicle within the i-th preset time period, where i is greater than or equal to 1.

[0096] Specifically, for each driving strategy combination corresponding to the own vehicle and the target vehicle, at the i-th preset time, for any vehicle among the own vehicle and the target vehicle, determine the acceleration corresponding to the different driving strategies adopted by the vehicle at the i-th preset time. The acceleration has been adopted for the i-1th preset duration The acceleration difference between By calculating the change in vehicle acceleration under different driving strategies, the dynamic changes in the vehicle's driving state are reflected.

[0097] Determine the inverse of the acceleration ratio between the acceleration difference and the preset acceleration value, where the preset acceleration value is the maximum acceleration a that the vehicle can adopt. max With the maximum deceleration a min By calculating the acceleration ratio and taking its opposite, we can get a negative value indicator that reflects the severity of the acceleration change, that is, The larger the negative value of the indicator (i.e. the closer the negative value is to 0), the smoother the acceleration change (i.e. the smaller it is), and the higher the driving comfort (the negative value is only used for comparison and does not directly represent the comfort. It is a quantitative representation of comfort, and the comfort increases as the negative value increases).

[0098] The inverse of the acceleration ratio corresponding to different driving strategies is determined as the comfort level of the vehicle corresponding to different driving strategies within the i-th preset time period. This provides a solution for quantitatively evaluating the comfort level of different driving strategies for the vehicle, which is helpful for subsequent comparison and selection of different driving strategies. It also helps the vehicle to evaluate the comfort level within different preset time periods based on the real-time traffic environment, road conditions, and its own driving status, and dynamically adjust the driving strategy according to the real-time traffic conditions. This helps to select a comfortable driving strategy during lane changing, reduce unnecessary acceleration and deceleration operations, and improve lane changing efficiency.

[0099] In some embodiments, based on safety and comfort, target driving strategies corresponding to the ego vehicle and the target vehicle within each preset time period are determined, including:

[0100] For any vehicle among the own vehicle and the target vehicle, the safety and comfort corresponding to the same driving strategy of the vehicles are weighted summed to obtain the corresponding benefit value of the vehicle under the driving strategy;

[0101] According to the benefit values ​​corresponding to the own vehicle under different driving strategies and the benefit values ​​corresponding to the target vehicle under different driving strategies, the target driving strategies corresponding to the own vehicle and the target vehicle within each preset time period are determined.

[0102] Specifically, when determining the target driving strategies for the ego vehicle and the target vehicle within each preset duration, each preset duration in the dynamic interaction between the ego vehicle and the target vehicle can be considered a game round, and the entire lane change process can be considered a repeated game consisting of multiple rounds. To find the optimal strategy in the game corresponding to each preset duration, a game payoff function is designed. This function can evaluate the performance of different driving strategy combinations from the perspectives of traffic safety (safety) and traffic comfort (comfort). After the first decision is made, the ego vehicle continues to make a second decision based on the driving status of the other vehicle and its own. This process is repeated until one vehicle successfully passes the conflict point, at which point the conflict relationship ends.

[0103] When calculating the benefit value of the ego vehicle under different driving strategies, the corresponding safety and comfort levels of the ego vehicle under each driving strategy are weighted and summed to obtain the corresponding benefit value of the ego vehicle under each driving strategy. Similarly, when calculating the benefit value of the target vehicle under different driving strategies, the corresponding safety and comfort levels of the target vehicle under each driving strategy are weighted and summed to obtain the corresponding benefit value of the target vehicle under each driving strategy. For example, the corresponding safety and comfort levels of the ego vehicle under the acceleration strategy are weighted and summed to obtain the corresponding benefit value of the ego vehicle under the acceleration strategy; the corresponding safety and comfort levels of the ego vehicle under the deceleration strategy are weighted and summed to obtain the corresponding benefit value of the ego vehicle under the deceleration strategy; and the corresponding safety and comfort levels of the ego vehicle under the constant speed strategy are weighted and summed to obtain the corresponding benefit value of the ego vehicle under the constant speed strategy. Similarly, the corresponding benefit values ​​of the target vehicle under the acceleration strategy, deceleration strategy, and constant speed strategy are obtained.

[0104] The benefit value can be calculated by referring to the following formula: U = αU a +βU s , α+β=1, where U is the benefit value, U s For safety, U ais comfort, α and β are weighting factors used to balance the importance of safety and comfort. For comprehensive consideration of safety and comfort, α = 0.6 and β = 0.4 are generally used. By using the weighted summation formula above, the two different dimensions of safety and comfort can be combined into a comprehensive benefit value, facilitating subsequent comparison and selection of the optimal driving strategy.

[0105] In addition, specifically, or for each driving strategy combination corresponding to the own vehicle and the target vehicle, the benefit value of the own vehicle and the benefit value of the target vehicle when the driving strategy combination is adopted are calculated; after obtaining the benefit value of the own vehicle and the benefit value of the target vehicle corresponding to each driving strategy combination, the target driving strategy combination is selected from each driving strategy combination, and the driving strategy of the own vehicle in the target driving strategy combination is determined as the target driving strategy corresponding to the own vehicle within each preset time length, and the driving strategy of the target vehicle in the target driving strategy combination is determined as the target driving strategy corresponding to the target vehicle within each preset time length.

[0106] By converting safety and comfort into a comprehensive benefit value through weighted summation, the vehicle can consider both safety and comfort when choosing a driving strategy, avoiding the limitations of single-indicator decision-making. Driving strategies are determined based on the benefit value, allowing the vehicle to maximize driving comfort while ensuring safety, thereby optimizing the entire driving process, driving more intelligently during lane changes, reducing the risk of traffic accidents, and improving traffic flow and overall road utilization efficiency.

[0107] In some embodiments, determining target driving strategies corresponding to the ego vehicle and the target vehicle within each preset time period based on the benefit values ​​corresponding to the ego vehicle under different driving strategies and the benefit values ​​corresponding to the target vehicle under different driving strategies includes:

[0108] The benefit values ​​corresponding to the own vehicle under different driving strategies and the benefit values ​​corresponding to the target vehicle under different driving strategies are combined to obtain a set of benefit values ​​corresponding to different driving strategy combinations, where the driving strategy combination includes the driving strategy corresponding to the own vehicle and the driving strategy corresponding to the target vehicle;

[0109] The sum of the two benefit values ​​in each benefit value set is determined, and the driving strategy combination corresponding to the benefit value set with the largest sum is determined as the target driving strategy corresponding to the own vehicle and the target vehicle respectively.

[0110] Specifically, according to the benefit value of the own vehicle and the benefit value of the target vehicle corresponding to each driving strategy combination, the benefit value sets corresponding to different driving strategy combinations can be determined, and the sum of the two benefit values ​​in each benefit value set can be calculated.

[0111] For example, for the driving strategy combination (3.0, -3.0), if the benefit value of the own vehicle under acceleration 3.0 is U1, and the benefit value of the target vehicle under deceleration -3.0 is U2, then the benefit sum value corresponding to the driving strategy combination (3.0, -3.0) is U=U1+U2.

[0112] For example, as shown in Table 1 below, there are benefit value combinations corresponding to different driving strategy combinations.

[0113] Table 1: Benefit value combinations corresponding to different driving strategy combinations

[0114]

[0115] By calculating the sum of the benefits, the overall contribution of both parties in each driving strategy combination is quantified, providing an objective basis for selecting the optimal strategy. The driving strategy combination corresponding to the benefit set with the largest sum is then determined as the target driving strategy for both the ego vehicle and the target vehicle. By combining and comparing the benefits of the ego vehicle and the target vehicle, the system not only considers the driving needs of the ego vehicle but also the possible reactions and interests of the target vehicle, maximizing overall benefits and achieving more comprehensive and intelligent decision-making.

[0116] All of the above optional technical solutions can be combined in any way to form optional embodiments of the present application, and will not be described in detail here.

[0117] The following are device embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0118] Figure 4 Schematic diagram of a vehicle lane changing device provided in an embodiment of the present application. Figure 4 As shown, the vehicle lane changing device includes:

[0119] The conflict position determination module 401 is configured to determine, upon determining that the ego vehicle intends to change lanes, a lane change conflict position corresponding to each adjacent lane of the ego vehicle, wherein the lane change conflict position is an intersection point between the ego vehicle and the lane line passed by the ego vehicle during the lane change process;

[0120] A lane determination module 402 is configured to determine a target lane from each adjacent lane based on a lane change conflict position corresponding to each adjacent lane;

[0121] The benefit determination module 403 is configured to determine the safety and comfort levels corresponding to different driving strategies adopted by the ego vehicle and a target vehicle within each preset time period, wherein the target vehicle is the vehicle located to the side and rear of the ego vehicle in the target lane and has the smallest distance from the ego vehicle. Driving strategies include acceleration, deceleration, and constant speed driving.

[0122] The lane change control module 404 is configured to determine the target driving strategies corresponding to the own vehicle and the target vehicle within each preset time period based on safety and comfort, and control the own vehicle to drive with the corresponding target driving strategies within the preset time period until either the own vehicle or the target vehicle passes the lane change conflict position corresponding to the target lane.

[0123] According to the technical solution provided in the embodiment of the present application, the traffic flow in the current lane, target lane, and non-target lane is comprehensively considered, so that the vehicle can make the optimal decision based on the global traffic status and individual preferences, effectively avoiding traffic bottlenecks and congestion during the lane change process, thereby improving overall traffic efficiency; and based on game theory, the lane change process is modeled as a game situation involving multiple parties, and a corresponding decision-making strategy is designed, so that the vehicle can more intelligently select the optimal driving strategy during the lane change process, thereby reducing the risk of traffic accidents and improving traffic flow and overall road utilization efficiency.

[0124] In some embodiments, the conflict position determination module 401 is configured to obtain a first distance between the own vehicle and a first vehicle and a driving speed of the first vehicle, where the first vehicle is an adjacent vehicle located in front of the own vehicle in the lane where the own vehicle is located; determine the distance difference between the first distance and the second distance, where the second distance is the product of the driving speed of the first vehicle and a preset coefficient; and determine that the own vehicle has an intention to change lanes when the distance difference is greater than the preset distance.

[0125] In some embodiments, the conflict position determination module 401 is configured to obtain the current position information and current driving speed of the own vehicle; generate the lane change trajectory corresponding to the lane change to each adjacent lane based on the current position of the own vehicle, the current driving speed of the own vehicle and the preset time required to complete the lane change; and determine the intersection of each lane change trajectory and the adjacent lane as the lane change conflict position corresponding to the adjacent lane.

[0126] In some embodiments, the lane determination module 402 is configured to determine a first conflict time for a second vehicle in each adjacent lane to reach the lane change conflict position, and to determine a second conflict time for the ego vehicle to reach the lane change conflict position; wherein the second vehicle is the vehicle in each adjacent lane that is located to the side and rear of the ego vehicle and has the shortest distance from the ego vehicle;

[0127] Determine the absolute value of the difference between the first conflict time and the second conflict time corresponding to each adjacent lane; and determine the adjacent lane corresponding to the largest absolute value among all absolute values ​​as the target lane.

[0128] In some embodiments, the benefit determination module 403 is configured to determine, for the i-th preset time period, a first time when the own vehicle arrives at the lane change conflict position when adopting different driving strategies based on a first distance between the own vehicle and the lane change conflict position at the beginning of the i-th preset time period and the driving speed of the own vehicle at the beginning of the i-th preset time period; determine a second time when the target vehicle arrives at the lane change conflict position when adopting different driving strategies based on a second distance between the target vehicle and the lane change conflict position at the beginning of the i-th preset time period and the driving speed of the target vehicle at the beginning of the i-th preset time period; determine the absolute value of the time difference between the first time corresponding to any driving strategy and the second time corresponding to any driving strategy, and determine the absolute value of all time differences as the safety degree corresponding to different driving strategy combinations of the own vehicle and the target vehicle within the i-th preset time period, where the driving strategy combination is the driving strategy adopted by the own vehicle and the driving strategy adopted by the target vehicle, where i is greater than or equal to 1.

[0129] In some embodiments, the benefit determination module 403 is configured to determine, for any vehicle among the own vehicle and the target vehicle, the acceleration difference between the acceleration corresponding to the different driving strategies adopted by the vehicle in the i-th preset time period and the acceleration adopted in the i-1-th preset time period; determine the inverse of the acceleration ratio between the acceleration difference and the preset acceleration value, where the preset acceleration value is the difference between the maximum acceleration and the maximum deceleration that the vehicle can adopt; and determine the inverse of the acceleration ratio corresponding to the different driving strategies as the comfort corresponding to the different driving strategies of the vehicle in the i-th preset time period, where i is greater than or equal to 1.

[0130] In some embodiments, the lane change control module 404 is configured to perform a weighted summation of the safety and comfort corresponding to the same driving strategy of the vehicle to obtain the benefit value corresponding to the vehicle under the driving strategy; based on the benefit value corresponding to the own vehicle under different driving strategies and the benefit value corresponding to the target vehicle under different driving strategies, determine the target driving strategies corresponding to the own vehicle and the target vehicle respectively within each preset time length.

[0131] In some embodiments, the lane change control module 404 is configured to combine the benefit values ​​corresponding to the own vehicle under different driving strategies and the benefit values ​​corresponding to the target vehicle under different driving strategies to obtain benefit value sets corresponding to different driving strategy combinations, where the driving strategy combination includes the driving strategy corresponding to the own vehicle and the driving strategy corresponding to the target vehicle; determine the sum of the two benefit values ​​in each benefit value set, and determine the driving strategy combination corresponding to the benefit value set with the largest sum as the target driving strategy corresponding to the own vehicle and the target vehicle respectively.

[0132] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0133] Figure 5 Schematic diagram of the electronic device 5 provided in the embodiment of the present application. Figure 5 As shown, the electronic device 5 of this embodiment includes: a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable by the processor 501. When the processor 501 executes the computer program 503, the steps of the above-mentioned method embodiments are implemented. Alternatively, when the processor 501 executes the computer program 503, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0134] The electronic device 5 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 5 may include but is not limited to a processor 501 and a memory 502. Those skilled in the art will appreciate that Figure 5 This is merely an example of the electronic device 5 and does not limit the electronic device 5 . The electronic device 5 may include more or fewer components than shown in the figure, or different components.

[0135] The processor 501 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0136] The memory 502 can be an internal storage unit of the electronic device 5, such as a hard disk or memory of the electronic device 5. The memory 502 can also be an external storage device of the electronic device 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. The memory 502 can also include both an internal storage unit of the electronic device 5 and an external storage device. The memory 502 is used to store computer programs and other programs and data required by the electronic device.

[0137] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0138] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium (such as a computer-readable storage medium). Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. Computer-readable storage media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0139] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A vehicle lane changing method, characterized in that: include: When it is determined that the ego vehicle intends to change lanes, determining a lane change conflict position corresponding to each adjacent lane in all adjacent lanes of the ego vehicle, the lane change conflict position being an intersection of the ego vehicle and a lane line passed by the ego vehicle during the lane change process; determining a target lane from each of the adjacent lanes according to a lane change conflict position corresponding to each of the adjacent lanes; Determining the safety and comfort levels corresponding to different driving strategies employed by the ego vehicle and a target vehicle within each preset time period, wherein the target vehicle is the vehicle located to the side and rear of the ego vehicle in the target lane and at the shortest distance from the ego vehicle, and the driving strategies include accelerating, decelerating, and driving at a constant speed; Based on the safety and comfort levels, the target driving strategies corresponding to the own vehicle and the target vehicle within each preset time period are determined, and the own vehicle is controlled to drive with the corresponding target driving strategies within the preset time period until either the own vehicle or the target vehicle passes the lane change conflict position corresponding to the target lane.

2. The method according to claim 1, characterized in that Determining that the vehicle has an intention to change lanes includes: Obtaining a first distance between the host vehicle and a first vehicle and a travel speed of the first vehicle, where the first vehicle is an adjacent vehicle located in front of the host vehicle in the lane where the host vehicle is located; determining a distance difference between the first distance and a second distance, the second distance being a product of a travel speed of the first vehicle and a preset coefficient; When the distance difference is greater than a preset distance, it is determined that the host vehicle has an intention to change lanes.

3. The method according to claim 1, characterized in that The determining of the lane change conflict position corresponding to each adjacent lane in all adjacent lanes of the own vehicle includes: Obtaining the current location information and current driving speed of the own vehicle; generating a lane change trajectory corresponding to each of the adjacent lanes based on the current position of the own vehicle, the current speed of the own vehicle, and a preset time required to complete the lane change; An intersection point between each lane change trajectory and the adjacent lane is determined as a lane change conflict position corresponding to the adjacent lane.

4. The method according to claim 1, wherein The determining of the target lane from each adjacent lane according to the lane change conflict position corresponding to each adjacent lane includes: Determining a first conflict time when a second vehicle in each adjacent lane reaches the lane change conflict position, and determining a second conflict time when the own vehicle reaches the lane change conflict position; wherein the second vehicle is a vehicle in each adjacent lane that is located to the rear of the own vehicle and has the shortest distance from the own vehicle; Determine the absolute value of the difference between the first conflict time and the second conflict time corresponding to each adjacent lane; The adjacent lane corresponding to the largest absolute value among all the absolute values ​​is determined as the target lane.

5. The method according to claim 1, wherein Determining the safety levels corresponding to the own vehicle and the target vehicle when using different driving strategies within each preset time period, including: For the i-th preset duration, determining, based on a first distance between the ego vehicle and the lane change conflict location at the start of the i-th preset duration and the driving speed of the ego vehicle at the start of the i-th preset duration, a first time at which the ego vehicle reaches the lane change conflict location when using different driving strategies; Determining, based on a second distance between the target vehicle and the lane change conflict position at the beginning of the i-th preset time period and a driving speed of the target vehicle at the beginning of the i-th preset time period, a second time for the target vehicle to arrive at the lane change conflict position when adopting different driving strategies; Determine the absolute value of the time difference between the first time corresponding to any driving strategy and the second time corresponding to any driving strategy, and determine the absolute value of all the time differences as the safety degree corresponding to different driving strategy combinations of the own vehicle and the target vehicle within the i-th preset time period, where the driving strategy combination is the driving strategy adopted by the own vehicle and the driving strategy adopted by the target vehicle, where i is greater than or equal to 1.

6. The method according to claim 1, characterized in that Determining the comfort levels corresponding to the own vehicle and the target vehicle when using different driving strategies within each preset time period, including: For any vehicle among the own vehicle and the target vehicle, determining the acceleration difference between the acceleration corresponding to the different driving strategies adopted by the vehicle during the i-th preset time period and the acceleration adopted during the i-1-th preset time period; Determining the inverse of an acceleration ratio between the acceleration difference and a preset acceleration value, wherein the preset acceleration value is the difference between a maximum acceleration and a maximum deceleration that the vehicle can adopt; The opposite of the acceleration ratio corresponding to the different driving strategies is determined as the comfort level corresponding to the different driving strategies of the vehicle within the i-th preset time period, where i is greater than or equal to 1.

7. The method according to claim 1, characterized in that Determining target driving strategies corresponding to the host vehicle and the target vehicle within each preset time period based on the safety and comfort levels, including: For any vehicle among the own vehicle and the target vehicle, a weighted sum of the safety and comfort corresponding to the same driving strategy of the vehicle is performed to obtain the benefit value corresponding to the vehicle under the driving strategy; The target driving strategies corresponding to the own vehicle and the target vehicle in each preset time period are determined according to the benefit values ​​corresponding to the own vehicle under different driving strategies and the benefit values ​​corresponding to the target vehicle under different driving strategies.

8. The method according to claim 7, characterized in that The determining, based on the benefit values ​​corresponding to the own vehicle under different driving strategies and the benefit values ​​corresponding to the target vehicle under different driving strategies, target driving strategies corresponding to the own vehicle and the target vehicle within each preset time period respectively includes: Combining the benefit values ​​corresponding to the own vehicle under different driving strategies and the benefit values ​​corresponding to the target vehicle under different driving strategies to obtain a benefit value set corresponding to different driving strategy combinations, wherein the driving strategy combination includes the driving strategy corresponding to the own vehicle and the driving strategy corresponding to the target vehicle; The sum of the two benefit values ​​in each benefit value set is determined, and the driving strategies corresponding to the benefit value set with the largest sum are combined to determine the target driving strategies corresponding to the own vehicle and the target vehicle respectively.

9. A vehicle lane changing device, characterized in that: include: a conflict position determination module configured to, upon determining that the ego vehicle intends to change lanes, determine a lane change conflict position corresponding to each adjacent lane of all adjacent lanes of the ego vehicle, wherein the lane change conflict position is an intersection point between the ego vehicle and a lane line passed by the ego vehicle during the lane change process; a lane determination module configured to determine a target lane from each of the adjacent lanes based on a lane change conflict position corresponding to each of the adjacent lanes; a benefit determination module configured to determine safety and comfort levels corresponding to different driving strategies employed by the ego vehicle and a target vehicle within each preset time period, wherein the target vehicle is a vehicle located to the side and rear of the ego vehicle in the target lane and at the shortest distance from the ego vehicle, and the driving strategies include accelerating, decelerating, and driving at a constant speed; The lane change control module is configured to determine the target driving strategies corresponding to the own vehicle and the target vehicle within each preset time period based on the safety and comfort levels, and control the own vehicle to drive with the corresponding target driving strategies within the preset time period until either the own vehicle or the target vehicle passes the lane change conflict position corresponding to the target lane.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images