A vehicle decision and control method and device considering safety and stability

Abstract

The application provides a vehicle decision and control method and device with safety and stability, comprising: acquiring a road surface parameter of a current lane, a driving state parameter of a current vehicle and a driving state parameter of an obstacle vehicle, wherein the obstacle vehicle is a vehicle driving in the current lane or a target lane; determining a lane change decision of the current vehicle according to the road surface parameter, the driving state parameter of the current vehicle and the driving state parameter of the obstacle vehicle; and controlling the current vehicle to change lanes to the target lane according to the lane change decision. The method makes a lane change decision based on the road surface parameter of the current lane and the driving state of the vehicle, provides a corresponding lane change decision under different road surface conditions, avoids unsafe conditions such as vehicle side slip, and improves the stability of the vehicle lane change process on the basis of ensuring the safety of the vehicle.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a vehicle decision-making and control method, system, device, and vehicle that takes into account both safety and stability. Background Technology

[0002] Local motion control of a vehicle refers to the process by which the vehicle control system plans a local motion trajectory to guide the vehicle safely, based on information such as the vehicle's status and traffic conditions, thereby controlling the vehicle to travel along that trajectory. For example, local motion control includes lane change control.

[0003] To address the issue of lane-changing decisions and control for vehicles, the industry typically plans corresponding lane-changing decisions based on the traffic scenario in which the vehicle is located, and then determines the lane-changing trajectory and speed based on the vehicle's current driving state, thereby controlling the vehicle to complete the lane change according to the lane-changing trajectory and speed. However, the above methods cannot guarantee the stability of the vehicle during lane changes, thus affecting driving safety. Summary of the Invention

[0004] This application provides a vehicle decision-making and control method that balances safety and stability. This method makes lane-changing decisions based on vehicle and road conditions, controlling lane changes while ensuring vehicle safety and improving stability during the lane-changing process. This application also provides a system, device, and vehicle corresponding to the above method.

[0005] Firstly, this application provides a vehicle decision-making and control method that balances safety and stability. The method includes:

[0006] The road surface parameters of the current lane, the driving status parameters of the current vehicle, and the driving status parameters of the obstacle vehicle are obtained, wherein the obstacle vehicle is a vehicle traveling in the current lane or the target lane;

[0007] The lane-changing decision of the current vehicle is determined based on the road surface parameters, the driving status parameters of the current vehicle, and the driving status parameters of the obstacle vehicle.

[0008] Based on the lane change decision, control the current vehicle to change lanes to the target lane.

[0009] In some possible implementations, determining the lane-changing decision of the current vehicle based on the road surface parameters, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle includes:

[0010] Based on the road surface parameters, the maximum permissible lane-changing speed of the current vehicle is determined, and based on the road surface parameters, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle, the minimum safe distance between the current vehicle and the obstacle vehicle is determined.

[0011] The lane change decision of the current vehicle is determined based on the maximum permissible lane change speed, the minimum safe distance, the driving status parameters of the current vehicle, and the driving status parameters of the obstacle vehicle.

[0012] In some possible implementations, determining the lane-changing decision of the current vehicle based on the maximum permissible lane-changing speed, the minimum safe distance, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle includes:

[0013] Based on the maximum permissible lane change speed, the minimum safe distance, and the current vehicle's speed, determine the current vehicle's deceleration strategy and lane change speed;

[0014] The lane-changing trajectory of the current vehicle is determined based on the driving status parameters of the current vehicle and the driving status parameters of the obstacle vehicle.

[0015] In some possible implementations, determining the maximum permissible lane-changing speed of the current vehicle based on the road surface parameters includes:

[0016] The stable lane change speed of the current vehicle is determined based on the road surface adhesion coefficient and the maximum road curvature, which are the road surface parameters.

[0017] The maximum permissible lane change speed of the current vehicle is determined based on the stable lane change speed and the speed limit of the current lane.

[0018] In some possible implementations, determining the minimum safe distance between the current vehicle and the obstacle vehicle based on the road surface parameters, the current vehicle's driving state parameters, and the obstacle vehicle's driving state parameters includes:

[0019] The maximum braking acceleration of the current vehicle is determined based on the road surface adhesion coefficient, which is a road surface parameter.

[0020] The minimum safe distance between the current vehicle and the obstacle vehicle is determined based on the maximum braking acceleration, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle.

[0021] In some possible implementations, the lane change decision includes multiple candidate lane change decisions, and determining the lane change decision for the current vehicle includes:

[0022] Based on the evaluation model, the evaluation results of the multiple candidate lane change decisions are determined;

[0023] Based on the evaluation results of the multiple candidate lane change decisions, the target lane change decision is determined from the multiple candidate lane change decisions.

[0024] In some possible implementations, determining the evaluation results of the multiple candidate lane change decisions based on the evaluation model includes:

[0025] Based on the artificial potential field method, the safety cost results of the multiple candidate lane change decisions are obtained;

[0026] Based on the curvature of the multiple lane change trajectories in the multiple candidate lane change decisions, the comfort cost result of the multiple candidate lane change decisions is obtained;

[0027] The evaluation results of the multiple candidate lane change decisions are determined based on the safety cost results and the comfort cost results.

[0028] Secondly, this application provides a vehicle decision-making and control system. The system includes a controller and an actuator, the controller storing instructions, and the actuator executing the instructions to cause the system to perform the method described in the first aspect or any implementation thereof.

[0029] Thirdly, this application provides a vehicle decision-making and control device, the device comprising:

[0030] The acquisition module is used to acquire the road surface parameters of the current lane, the driving status parameters of the current vehicle, and the driving status parameters of the obstacle vehicle, wherein the obstacle vehicle is a vehicle traveling in the current lane or the target lane.

[0031] The determination module is used to determine the lane-changing decision of the current vehicle based on the road surface parameters, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle.

[0032] The control module is used to control the current vehicle to change lanes to the target lane based on the lane change decision.

[0033] In some possible implementations, the determining module is specifically used for:

[0034] Based on the road surface parameters, the maximum permissible lane-changing speed of the current vehicle is determined, and based on the road surface parameters, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle, the minimum safe distance between the current vehicle and the obstacle vehicle is determined.

[0035] The lane change decision of the current vehicle is determined based on the maximum permissible lane change speed, the minimum safe distance, the driving status parameters of the current vehicle, and the driving status parameters of the obstacle vehicle.

[0036] In some possible implementations, the determining module is specifically used for:

[0037] Based on the maximum permissible lane change speed, the minimum safe distance, and the current vehicle's speed, determine the current vehicle's deceleration strategy and lane change speed;

[0038] The lane-changing trajectory of the current vehicle is determined based on the driving status parameters of the current vehicle and the driving status parameters of the obstacle vehicle.

[0039] In some possible implementations, the determining module is specifically used for:

[0040] The stable lane change speed of the current vehicle is determined based on the road surface adhesion coefficient and the maximum road curvature, which are the road surface parameters.

[0041] The maximum permissible lane change speed of the current vehicle is determined based on the stable lane change speed and the speed limit of the current lane.

[0042] In some possible implementations, the determining module is specifically used for:

[0043] The maximum braking acceleration of the current vehicle is determined based on the road surface adhesion coefficient, which is a road surface parameter.

[0044] The minimum safe distance between the current vehicle and the obstacle vehicle is determined based on the maximum braking acceleration, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle.

[0045] In some possible implementations, the lane change decision includes multiple candidate lane change decisions, and the determining module is specifically used for:

[0046] Based on the evaluation model, the evaluation results of the multiple candidate lane change decisions are determined;

[0047] Based on the evaluation results of the multiple candidate lane change decisions, the target lane change decision is determined from the multiple candidate lane change decisions.

[0048] In some possible implementations, the determining module is specifically used for:

[0049] Based on the artificial potential field method, the safety cost results of the multiple candidate lane change decisions are obtained;

[0050] Based on the curvature of the multiple lane change trajectories in the multiple candidate lane change decisions, the comfort cost result of the multiple candidate lane change decisions is obtained;

[0051] The evaluation results of the multiple candidate lane change decisions are determined based on the safety cost results and the comfort cost results.

[0052] Fourthly, this application provides a vehicle. The vehicle includes the system described in the second aspect of this application.

[0053] Based on the implementation methods provided in the above aspects, this application can be further combined to provide more implementation methods.

[0054] Based on the above description, it can be seen that the technical solution of this application has the following beneficial effects:

[0055] This method first acquires the road surface parameters of the current lane, the driving state parameters of the current vehicle, and the driving state parameters of obstacle vehicles, where obstacle vehicles are vehicles traveling in the current lane or the target lane. Then, based on the road surface parameters, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicles, it determines the lane-changing decision for the current vehicle and controls the current vehicle to change lanes to the target lane according to the lane-changing decision. This method makes lane-changing decisions based on the road surface parameters of the current lane and the vehicle's driving state, providing corresponding lane-changing decisions under different road conditions, avoiding unsafe situations such as vehicle skidding, and improving the stability of the vehicle's lane-changing process while ensuring vehicle safety. Attached Figure Description

[0056] The above and other features, advantages, and aspects of the embodiments of this application will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0057] Figure 1 A flowchart illustrating a vehicle decision-making and control method that balances safety and stability, provided as an embodiment of this application;

[0058] Figure 2 This application provides a schematic diagram of a traffic scenario involving a vehicle changing lanes, as illustrated in an embodiment of the present application.

[0059] Figure 3 This application provides a schematic diagram of a traffic scenario involving a vehicle changing lanes, as illustrated in an embodiment of the present application.

[0060] Figure 4 A schematic diagram of the road potential field provided in an embodiment of this application;

[0061] Figure 5 A top view of the road potential field under different road surface adhesion coefficients provided in this application embodiment;

[0062] Figure 6 This application provides a schematic diagram of a traffic scenario involving a vehicle changing lanes, as illustrated in an embodiment of the present application.

[0063] Figure 7A simulation result diagram illustrating vehicle decision-making and control provided in an embodiment of this application;

[0064] Figure 8 This application provides a schematic diagram of a traffic scenario involving a vehicle changing lanes, as illustrated in an embodiment of the present application.

[0065] Figure 9 A simulation result diagram illustrating vehicle decision-making and control provided in an embodiment of this application;

[0066] Figure 10 This is a schematic diagram of the structure of a vehicle decision-making and control device provided in an embodiment of this application. Detailed Implementation

[0067] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While some embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this application. It should be understood that the drawings and embodiments of this application are for illustrative purposes only and are not intended to limit the scope of protection of this application.

[0068] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0069] It should be noted that the concepts of "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0070] It should be noted that the terms "a" and "a plurality of" used in this application are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0071] To facilitate understanding of the technical solution of this application, the specific application scenarios of this application are described below.

[0072] Vehicle decision planning includes global path planning, behavioral decision-making, and local motion planning. Local motion planning refers to planning a local trajectory that can guide the vehicle to drive safely based on information such as vehicle status and traffic scenario, thereby controlling the vehicle to drive according to the planned local trajectory.

[0073] To address the aforementioned local motion planning problem, the industry typically plans the desired local trajectory based on the traffic scenario in which the vehicle is located, and then controls the vehicle's speed based on the vehicle's driving state, thereby achieving local motion planning.

[0074] However, the above methods only consider the vehicle's safety in avoiding collisions when performing local motion planning, without considering the vehicle's dynamic stability while tracking a local trajectory. Furthermore, these methods do not account for the impact of road conditions on local trajectory tracking. For example, different road conditions can affect factors such as the vehicle's safe distance and lane-changing speed. When a vehicle is traveling at high speed and making an emergency lane change, the above methods may cause the vehicle to skid during the lane change process, affecting driving safety.

[0075] Based on this, embodiments of this application provide a vehicle decision-making and control method that balances safety and stability. The method first acquires the road surface parameters of the current lane, the driving state parameters of the current vehicle, and the driving state parameters of an obstacle vehicle, wherein the obstacle vehicle is a vehicle traveling in the current lane or a target lane. Then, based on the road surface parameters, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle, the method determines the lane-changing decision for the current vehicle and controls the current vehicle to change lanes to the target lane according to the lane-changing decision. This method makes lane-changing decisions based on the road surface parameters of the current lane and the vehicle's driving state, providing corresponding lane-changing decisions under different road conditions, avoiding unsafe situations such as vehicle skidding, and improving the stability of the vehicle's lane-changing process while ensuring vehicle safety.

[0076] Next, the vehicle decision-making and control method that balances safety and stability, as provided in the embodiments of this application, will be described in detail with reference to the accompanying drawings.

[0077] See Figure 1 The diagram illustrates a vehicle decision-making and control method that balances safety and stability. This method can be executed by the vehicle decision-making and control system and specifically includes the following steps:

[0078] S101: The vehicle decision and control system acquires the road surface parameters of the current lane, the driving status parameters of the current vehicle, and the driving status parameters of the obstacle vehicle, wherein the obstacle vehicle is a vehicle traveling in the current lane or the target lane.

[0079] Specifically, the vehicle decision and control system can fuse vehicle driving data and driving environment data collected by the vehicle perception system to obtain the road surface parameters of the current lane, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle.

[0080] Among them, the road surface parameters of the current lane represent the road surface conditions of the lane where the current vehicle is located, and may include one or more of the following: road surface adhesion coefficient and maximum road curvature between the current lane and the target lane; the driving state parameters of the current vehicle represent the driving state of the current vehicle, such as the current vehicle speed and the current vehicle's location information; the driving state parameters of the obstacle vehicle represent the driving state of the obstacle vehicle, such as the obstacle vehicle speed and the obstacle vehicle's location information. The obstacle vehicle is a vehicle traveling in the current lane or the target lane, that is, a vehicle that may pose an obstacle to the current vehicle during the current vehicle's driving or lane changing process.

[0081] S102: The vehicle decision and control system determines the lane change decision of the current vehicle based on road surface parameters, the current vehicle's driving status parameters, and the driving status parameters of the obstacle vehicle.

[0082] Specifically, the vehicle decision and control system can determine the maximum permissible lane-changing speed of the current vehicle based on road surface parameters. Then, based on the road surface parameters, the current vehicle's driving state parameters, and the obstacle vehicle's driving state parameters, it determines the minimum safe distance between the current vehicle and the obstacle vehicle. Finally, based on the maximum permissible lane-changing speed, the minimum safe distance, the current vehicle's driving state parameters, and the obstacle vehicle's driving state parameters, it determines the current vehicle's lane-changing decision. It should be noted that the maximum permissible lane-changing speed is used to ensure the dynamic stability of the current vehicle during lane changing, and the minimum safe distance is used to avoid collisions between the current vehicle and the obstacle vehicle. In this embodiment, both the maximum permissible lane-changing speed and the minimum safe distance are related to road surface parameters. The maximum permissible lane-changing speed and the minimum safe distance differ depending on the road surface conditions. For example, when the road surface conditions are poor, the maximum permissible lane-changing speed will be lower, and the minimum safe distance will be higher to ensure safety and stability during lane changing.

[0083] In some possible implementations, the vehicle decision and control system can determine the stable lane change speed of the current lane based on the road surface adhesion coefficient and the maximum road curvature between the current lane and the target lane. Then, based on the stable lane change speed and the speed limit of the current lane, it can determine the maximum permissible lane change speed of the current vehicle, thereby determining the maximum permissible lane change speed that satisfies traffic rule restrictions and vehicle stability.

[0084] Furthermore, the vehicle decision and control system can determine the maximum braking acceleration of the current vehicle based on the road surface adhesion coefficient. Based on the maximum braking acceleration, the current vehicle's driving state parameters, and the obstacle vehicle's driving state parameters, it can determine the minimum safe distance between the current vehicle and the obstacle vehicle, thereby determining the minimum safe distance that meets the vehicle's driving safety requirements and avoiding a collision between the current vehicle and the obstacle vehicle.

[0085] Furthermore, the vehicle decision and control system can determine the deceleration strategy and lane change speed of the current vehicle based on the maximum permissible lane change speed, the minimum safe distance, and the current vehicle speed. Then, based on the driving state parameters of the current vehicle and the driving state parameters of the obstacle vehicle, it can determine the lane change trajectory of the current vehicle so as to control the current vehicle to change lanes according to the lane change speed and lane change trajectory.

[0086] The lane-changing decision-making process in this application embodiment will be described below in conjunction with specific traffic scenarios.

[0087] See Figure 2 A traffic scenario diagram of a vehicle changing lanes is given. Here, (x0, y0) represents the current position of the vehicle, (x1, y1) represents the position of the obstacle vehicle, and (x... t ,y t (x0, y0), (x1, y1), and (x2, y2) represent the target position of the vehicle after the lane change. The vehicle decision and control system can use (x0, y0), (x1, y1), and (x2, y2) to represent the target position of the vehicle after the lane change. t ,y t Generate lane change trajectory, where d represents the lateral distance between the current vehicle's position and the target position. Typically, d can be set to the lane width, for example, d = 3.5m. v This represents the desired distance between the target location and the obstacle vehicle, which can be expressed as l v Defined as vehicle body length, for example, l v =5m, S1 represents the distance between the current vehicle and the obstacle vehicle, S h This indicates the maximum lane change distance. When the distance between the current vehicle and the obstacle vehicle is less than the maximum lane change distance, the current vehicle must change lanes; otherwise, a collision may occur. S h It can be determined based on the actual driving conditions. For example, when the vehicle is currently traveling on a highway, there can be an S... h =35m, S d S represents the decision distance. When the distance between the current vehicle and the obstacle vehicle is greater than the decision distance, the current vehicle can continue driving normally in the current lane. When the distance between the current vehicle and the obstacle vehicle is less than or equal to the decision distance, the current vehicle may consider whether to change lanes. d It can be determined based on the actual driving conditions. For example, when the vehicle is currently traveling on a highway, there can be an S... d =120m, S a The minimum safe distance is determined by the road surface adhesion coefficient, the current vehicle's speed, and the speeds of the obstacle vehicles. Specifically, when there are multiple obstacle vehicles, the minimum safe distance can be expressed as:

[0088]

[0089] Among them, Sai represents the minimum safe distance between the ego vehicle and the i-th obstacle vehicle, vx represents the speed of the ego vehicle, v i represents the speed of the i-th obstacle vehicle, which can be obtained according to the speed of the ego vehicle and the relative speed, Δt represents the reaction time of the perception system of the ego vehicle, for example, Δt=0.1s, S0 represents the minimum parking distance between the ego vehicle and the target vehicle, the minimum parking distance can be set as 1.5 times the vehicle body length, for example, S0=7.5m, a x_max represents the maximum braking acceleration of the ego vehicle, which is related to the road adhesion coefficient μ, for example, a x_max =-0.8μg, where g is the gravitational acceleration.

[0090] When S1 > S d , the ego vehicle does not need to change lanes, and can continue to travel in the current lane at the original speed. When S1 ≤ S d and v x < v1, the speed of the ego vehicle is relatively low, no collision with the obstacle vehicle will occur, and no lane change is required.

[0091] When S a < S1 ≤ S d and v x ≥ v1, the ego vehicle will collide with the obstacle vehicle if it continues to travel, and the lane change decision at this time can be: if v x ≤ v xh , then controlling the vehicle to change lanes by tracking the lane change trajectory at the current speed; if v x > v xh , then controlling the ego vehicle to decelerate with a deceleration strategy of acceleration a x = -0.4μg until decelerating to v x = v xh , and then changing lanes by tracking the lane change trajectory at the speed of v xh , wherein v xh is the maximum allowable lane change speed, which can be expressed as v xh = max(v κ ,v t ), v k represents the stable lane change speed of the ego vehicle, which is related to the road adhesion coefficient μ, k max represents the maximum road curvature of the current lane and the target lane, v t is the speed limit of the current lane, for example, when the ego vehicle is driving on a highway, v t = 60km / h.

[0092] When the vehicle decision and control system controls the ego vehicle to decelerate with a deceleration strategy of acceleration a x = -0.4μg, but until Sh <S1≤S a It had not yet decelerated to v x =v xh At this point, control the vehicle to accelerate at speed a. x A deceleration strategy of -0.8 μg is used to reduce speed until the speed reaches v. x =v xh Then with v xh The vehicle changes lanes by tracking the speed of the lane change trajectory.

[0093] When the vehicle decision and control system controls the current vehicle to accelerate a x A deceleration strategy of -0.8 μg is used to reduce speed, but only until S1 ≤ S h It had not yet decelerated to v x =v xh To avoid collisions with obstacle vehicles, the vehicle changes lanes by following the lane-changing trajectory at its current speed.

[0094] The above lane change decision is aimed at Figure 2 In traffic scenarios where there is only an obstacle vehicle in the current lane, when there is also an obstacle vehicle in the target lane, the lane-changing decision also needs to consider the speed and position relationship between the current vehicle and the obstacle vehicle.

[0095] Specifically, see Figure 3 The diagram illustrates a traffic scenario involving a vehicle changing lanes. There is an obstacle vehicle 1 ahead of the current vehicle in its current lane, an obstacle vehicle 2 ahead of the target lane, and an obstacle vehicle 3 behind the target lane.

[0096] For the traffic scenario described above, for vehicle 2 with obstacles, when v2≥v x And S2≥v x Δt+1.5l v or v2 <v x S2>S1 and S a2 ≤S a1 When changing lanes, the system controls the current vehicle to follow the lane-changing trajectory at its current speed. The first condition ensures that the current vehicle's perception system has a sufficiently long response time to maintain the distance between vehicles, while the second condition ensures that changing lanes to the target lane is safer than staying in the current lane.

[0097] For obstacle vehicle 3, when v3≤v x And S3≥v3Δt+1.5l v or v3>v x And S3≥S a3When the current vehicle is controlled to change lanes at the current speed, it tracks the lane change trajectory. The first condition is to ensure that the obstacle vehicle 3's vehicle perception system has a sufficiently long response time to ensure the distance between vehicles. The second condition is to ensure that after changing lanes to the target lane, the obstacle vehicle 3 has enough time to brake to ensure the safety of vehicle driving.

[0098] When the above conditions are not met, in order to avoid a collision with the obstacle vehicle, lane changing can be avoided, and the vehicle can brake at its maximum acceleration a. x_max =―0.8μg controls vehicle deceleration.

[0099] In some possible implementations, lane change decision includes multiple candidate lane change decisions. The vehicle decision and control system can determine the evaluation results of multiple candidate lane change decisions based on the evaluation model, and then determine the target lane change decision from multiple candidate lane change decisions based on the evaluation results of multiple candidate lane change decisions.

[0100] Specifically, the evaluation model can include safety evaluation and comfort evaluation. The vehicle decision and control system can obtain the safety cost results of multiple candidate lane change decisions based on the artificial potential field method, and obtain the comfort cost results of multiple candidate lane change decisions based on the curvature of multiple lane change trajectories in multiple candidate lane change decisions. Thus, the evaluation results of multiple candidate lane change decisions can be determined based on the safety cost results and comfort cost results.

[0101] The method for determining target lane change decisions in the embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0102] against Figure 2 In the traffic scenario shown, where a vehicle is changing lanes, in some possible implementations, the current target position (x) of the vehicle is... t ,y t x in ) t It can be positioned one vehicle length in front of the obstacle vehicle, and y t It can be between 2.5m and 4m to the left of the obstacle vehicle, where multiple y-axis views of the current vehicle are within range. t The lateral spacing between them can be 0.25m, thereby generating multiple candidate lane change decisions that include multiple candidate lane change trajectories.

[0103] The vehicle decision and control system can use a fifth-order polynomial equation to describe the candidate lane change trajectory, which can be expressed as:

[0104] y = A T X (2)

[0105] Where A = [a0, a1, a2, a3, a4, a5] T X = [1, x, x 2 ,x3 ,x 4 ,x 5 ] T a i The coefficients of the polynomial are represented by (x,y), and the longitudinal and lateral coordinates of the candidate lane change trajectory are represented by (x,y).

[0106] When the vehicle changes lanes, the boundary constraints of the fifth-degree polynomial equation are:

[0107]

[0108] Where κ represents the road curvature. Based on the boundary constraints, the coefficient matrix can be obtained as follows:

[0109]

[0110] Therefore, the candidate lane change trajectory based on the fifth-order polynomial equation can be obtained as follows:

[0111]

[0112] In this embodiment, an evaluation model including safety and comfort assessments is constructed to evaluate multiple candidate lane-change trajectories. Specifically, the cost function of the evaluation model can be:

[0113] J i =w s J si +w c J ci (6)

[0114] Among them, J i Let w represent the cost function of the i-th candidate lane change trajectory. s and w c J represents the weight of safety and comfort evaluations. si and J ci Let J represent the safety evaluation cost function and the comfort evaluation cost function of the i-th candidate lane change trajectory. In some possible implementations, J... si J can be represented by the sum of the potential fields of the i-th candidate lane change trajectory. ci It can be represented by the sum of the curvatures of the i-th candidate lane change trajectory.

[0115] Specifically, a vehicle-road risk situation field is constructed based on the artificial potential field method. This risk situation field can include a road potential field and an obstacle vehicle potential field. The road potential field is determined by the road boundary line and can be expressed as U using trigonometric and exponential functions. road =A(y)U w Where A(y) represents the potential field amplitude as it varies with the horizontal coordinate y, and U wLet A(y) and U be the shape functions of the road potential field. w It can be represented as:

[0116]

[0117]

[0118] Among them, y c1 and y c2 p represents the lateral coordinates of the current lane and the target lane. m This represents the potential field amplitude along the lane divider, for example, p. m =0.5, r w This represents the width of the current lane, for example, r. w =3.5m, k represents the shape function U w The shape parameters, for example, k=5.

[0119] against Figure 3 In a traffic scenario involving lane changing, the current vehicle's speed is 110 km / h, obstacle vehicle 1's speed is 40 km / h, obstacle vehicle 2's speed is 100 km / h, and obstacle vehicle 3's speed is 70 km / h. When the road surface adhesion coefficient is 1, the generated road potential field is as follows: Figure 4 As shown in the figure. The top-view results of the road potential field under different pavement adhesion coefficients are as follows: Figure 5 As shown, where, Figure 5 (a) in the figure represents the result when the road surface adhesion coefficient is 1. Figure 5 (b) shows the result when the road surface adhesion coefficient is 0.5. It can be seen that the worse the road surface adhesion conditions, the larger the longitudinal potential field, which is beneficial to avoiding longitudinal collisions.

[0120] Furthermore, the obstacle vehicle potential field can be represented by the distance, relative speed, and road adhesion coefficient between the current vehicle and the obstacle vehicle. The smaller the distance, the greater the relative speed, and the smaller the road adhesion coefficient between the current vehicle and the obstacle vehicle, the greater the probability of collision between the current vehicle and the obstacle vehicle. Therefore, the obstacle vehicle potential field of the i-th obstacle vehicle can be expressed as:

[0121] U obs (i)=U obsx (i)U obsy (i) (9)

[0122] Among them, U obsx (i) and U obsy (i) represents the longitudinal and lateral potential fields of the obstacle vehicle, and we have:

[0123]

[0124]

[0125] Among them, w v The width of the obstacle vehicle, for example, is w. v =2m, σ x and σ y The longitudinal and transverse kernel widths of the potential field function are represented by, for example, σ. y =1,σ x =λ v σ0 / μ, where σ0 is the baseline kernel width, for example, σ0 = 5.

[0126] Thus, the safety evaluation result J of the i-th candidate lane change trajectory can be obtained. si =U road +U obs (i).

[0127] S103: The vehicle decision and control system controls the current vehicle to change lanes to the target lane based on the lane change decision.

[0128] Specifically, the vehicle decision and control system can control the current vehicle to change lanes to the target lane based on the lane change decision, using a trajectory tracking control model and a stability control model.

[0129] In some possible implementations, the vehicle decision and control system can use model predictive control theory to construct a trajectory tracking control model, thereby determining the current front wheel steering angle and longitudinal force of the vehicle; and construct a stability control model based on sliding mode control to determine the current vehicle's active yaw moment, thereby determining the longitudinal force of each wheel of the current vehicle, controlling the vehicle to track the lane change trajectory and change lanes to the target lane.

[0130] This method first acquires the road surface parameters of the current lane, the driving state parameters of the current vehicle, and the driving state parameters of obstacle vehicles, where obstacle vehicles are vehicles traveling in the current lane or the target lane. Then, based on the road surface parameters, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicles, it determines the lane-changing decision for the current vehicle and controls the current vehicle to change lanes to the target lane according to the lane-changing decision. This method makes lane-changing decisions based on the road surface parameters of the current lane and the vehicle's driving state, providing corresponding lane-changing decisions under different road conditions, avoiding unsafe situations such as vehicle skidding, and improving the stability of the vehicle's lane-changing process while ensuring vehicle safety.

[0131] To intuitively demonstrate the control effect of the vehicle decision-making and control method that balances safety and stability provided in the embodiments of this application, a detailed explanation will be given below with reference to two specific application examples.

[0132] Figure 6A traffic scenario diagram of a vehicle changing lanes is provided. In this scenario, the current lane forms a connecting road surface due to the change in the road surface adhesion coefficient. Specifically, the road surface adhesion coefficient is 0.8 from 0 to 85m, and the road surface adhesion coefficient is 0.5 after 85m. The current vehicle speed is 110km / h, obstacle vehicle 1 is located 80m ahead of the current lane, and obstacle vehicle 2 is located 150m ahead of the target lane.

[0133] In the above traffic scenario, the current lane needs to perform two lane changes, as shown in the simulation results diagram. Figure 7 As shown. Among them, Figure 7 (a) in the diagram represents the current lane-changing trajectory of the vehicle. Figure 7 In the figure, (b) represents the current longitudinal velocity and longitudinal force of the vehicle. Figure 7 In the figure, (c) represents the current lateral acceleration and front wheel steering angle of the vehicle. Figure 7 In the figure, (d) represents the current longitudinal acceleration of the vehicle. Figure 7 In the diagram, (e) represents the yaw rate of the current vehicle. It can be seen that the current vehicle first decelerates to approximately 90 km / h, initiates its first lane change at a longitudinal position of approximately 24 m, and completes the first lane change at a longitudinal position of approximately 85 m. Then, due to the change in the road surface adhesion coefficient, it decelerates again to approximately 70 km / h and completes its second lane change at a longitudinal position of approximately 155 m. The current vehicle exhibits good stability throughout the entire lane change process.

[0134] Figure 8 A traffic scenario diagram of a vehicle changing lanes is provided. In this diagram, the road surface adhesion coefficient of the current lane is 0.7, the speed of the current vehicle is 100 km / h, obstacle vehicle 1 is located 90 m ahead of the current lane, obstacle vehicle 2 is located 72 m ahead of the target lane and its speed is 65 km / h, and obstacle vehicle 3 is located 45 m behind the target lane and its speed is 100 km / h.

[0135] In the above traffic scenario, the current lane needs to perform two lane changes, as shown in the simulation results diagram. Figure 9 As shown. Among them, Figure 9 (a) in the diagram represents the current lane-changing trajectory of the vehicle. Figure 9 In the figure, (b) represents the current longitudinal velocity and longitudinal force of the vehicle. Figure 9 In the figure, (c) represents the current lateral acceleration and front wheel steering angle of the vehicle. Figure 9 In the figure, (d) represents the current longitudinal acceleration of the vehicle. Figure 9In the diagram, (e) represents the yaw rate of the current vehicle. It can be seen that the current vehicle first decelerates to approximately 85 km / h, initiates its first lane change at a longitudinal position of approximately 30 m, and completes the first lane change at a longitudinal position of approximately 95 m. Then, it initiates its second lane change and completes the second lane change at a longitudinal position of approximately 140 m. The current vehicle exhibits good stability throughout the entire lane change process.

[0136] The simulation results of the two application examples above show that the vehicle decision-making and control method that balances safety and stability provided in this application makes lane-changing decisions based on the road surface parameters of the current lane and the vehicle's driving state. It provides corresponding lane-changing decisions under different road conditions, avoids unsafe conditions such as vehicle skidding, and improves the stability of the vehicle's lane-changing process while ensuring vehicle safety.

[0137] Based on the vehicle decision-making and control method that balances safety and stability provided in the embodiments of this application, the embodiments of this application also provide a vehicle decision-making and control device corresponding to the above method. The units / modules described in the embodiments of this application can be implemented in software or hardware. The names of the units / modules do not, in certain circumstances, constitute a limitation on the unit / module itself.

[0138] See Figure 10 The schematic diagram shown illustrates the structure of a vehicle decision-making and control device 1000, which includes:

[0139] The acquisition module 1001 is used to acquire the road surface parameters of the current lane, the driving status parameters of the current vehicle, and the driving status parameters of the obstacle vehicle. The obstacle vehicle is a vehicle traveling in the current lane or the target lane.

[0140] The determination module 1002 is used to determine the lane change decision of the current vehicle based on road surface parameters, the current vehicle's driving status parameters, and the obstacle vehicle's driving status parameters.

[0141] The control module 1003 is used to control the current vehicle to change lanes to the target lane based on the lane change decision.

[0142] In some possible implementations, module 1002 is specifically used for:

[0143] Based on road surface parameters, determine the maximum permissible lane-changing speed of the current vehicle, and based on road surface parameters, the current vehicle's driving status parameters, and the obstacle vehicle's driving status parameters, determine the minimum safe distance between the current vehicle and the obstacle vehicle.

[0144] The lane change decision for the current vehicle is determined based on the maximum permissible lane change speed, the minimum safe distance, the current vehicle's driving status parameters, and the driving status parameters of the obstacle vehicle.

[0145] In some possible implementations, module 1002 is specifically used for:

[0146] Based on the maximum permissible lane change speed, the minimum safe distance, and the current vehicle's speed, determine the current vehicle's deceleration strategy and lane change speed;

[0147] The lane-changing trajectory of the current vehicle is determined based on the current vehicle's driving status parameters and the driving status parameters of the obstacle vehicle.

[0148] In some possible implementations, module 1002 is specifically used for:

[0149] The stable lane-changing speed of the current vehicle is determined based on the road surface adhesion coefficient and the maximum road curvature, which are road surface parameters.

[0150] Determine the maximum permissible lane change speed for the current vehicle based on the stable lane change speed and the speed limit of the current lane.

[0151] In some possible implementations, module 1002 is specifically used for:

[0152] The maximum braking acceleration of the vehicle at present is determined based on the road surface adhesion coefficient, which is a road surface parameter.

[0153] The minimum safe distance between the current vehicle and the obstacle vehicle is determined based on the maximum braking acceleration, the current vehicle's driving status parameters, and the obstacle vehicle's driving status parameters.

[0154] In some possible implementations, lane change decision-making includes multiple candidate lane change decisions, and the determination module 1002 is specifically used for:

[0155] Based on the evaluation model, the evaluation results of multiple candidate lane change decisions are determined;

[0156] Based on the evaluation results of multiple candidate lane change decisions, the target lane change decision is determined from the multiple candidate lane change decisions.

[0157] In some possible implementations, module 1002 is specifically used for:

[0158] Based on the artificial potential field method, the safety cost results of multiple candidate lane change decisions are obtained;

[0159] Based on the curvature of multiple lane change trajectories in multiple candidate lane change decisions, the comfort cost results of multiple candidate lane change decisions are obtained.

[0160] Based on the safety cost results and comfort cost results, the evaluation results of multiple candidate lane change decisions are determined.

[0161] The vehicle decision and control device 1000 according to the embodiments of this application can correspondingly execute the methods described in the embodiments of this application, and the above and other operations and / or functions of each module / unit of the vehicle decision and control device 1000 are respectively for implementing Figure 1 For the sake of brevity, the corresponding processes of each method in the illustrated embodiments will not be described in detail here.

[0162] This application also provides a vehicle decision-making and control system, which includes a controller and an actuator. The controller stores instructions, and the actuator executes these instructions, causing the vehicle decision-making and control system to perform vehicle decision-making and control methods.

[0163] This application also provides a vehicle. The vehicle includes the vehicle decision and control system described above.

[0164] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

[0165] While several specific implementation details are included in the foregoing discussion, these should not be construed as limiting the scope of this application. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0166] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A vehicle decision-making and control method that balances safety and stability, characterized in that, The method includes: The road surface parameters of the current lane, the driving status parameters of the current vehicle, and the driving status parameters of the obstacle vehicle are obtained, wherein the obstacle vehicle is a vehicle traveling in the current lane or the target lane; The stable lane change speed of the current vehicle is determined based on the road surface adhesion coefficient and the maximum road curvature, which are the road surface parameters. The maximum permissible lane change speed of the current vehicle is determined based on the stable lane change speed and the speed limit of the current lane; Based on the road surface parameters, the driving status parameters of the current vehicle, and the driving status parameters of the obstacle vehicle, determine the minimum safe distance between the current vehicle and the obstacle vehicle; The lane change decision of the current vehicle is determined based on the maximum permissible lane change speed, the minimum safe distance, the driving status parameters of the current vehicle, and the driving status parameters of the obstacle vehicle. Based on the lane change decision, the front wheel steering angle and longitudinal force of the current vehicle are determined using a trajectory tracking control model constructed with model predictive control theory, and the active yaw moment of the current vehicle is determined using a stability control model constructed with sliding mode control. Control the current vehicle to follow the trajectory of the lane change decision and change lanes to the target lane; The process of determining the lane-changing decision for the current vehicle includes: When the minimum safe distance is less than the distance between the current vehicle and the obstacle vehicle, the distance between the current vehicle and the obstacle vehicle is less than or equal to the decision distance, and the speed of the current vehicle is greater than or equal to the speed of the obstacle vehicle, if the speed of the current vehicle is less than or equal to the maximum permissible lane change speed, the current vehicle is controlled to follow the trajectory of the lane change decision at the current speed to change lanes; if the speed of the current vehicle is greater than the maximum permissible lane change speed, the current vehicle is controlled to decelerate with an acceleration of -0.4μg until it decelerates to the maximum permissible lane change speed, and then follows the trajectory of the lane change decision at the maximum permissible lane change speed to change lanes. If the current vehicle decelerates at the acceleration of -0.4μg, and the distance between the current vehicle and the obstacle vehicle is between the limit lane change distance and the minimum safe distance, but the vehicle has not decelerated to the maximum permissible lane change speed, the current vehicle is controlled to continue decelerating at the acceleration of -0.8μg until it decelerates to the maximum permissible lane change speed. Then, the vehicle follows the trajectory of the lane change decision and changes lanes at the maximum permissible lane change speed. Here, μ is the road surface adhesion coefficient, and g is the gravitational acceleration.

2. The method according to claim 1, characterized in that, The step of determining the lane-changing decision of the current vehicle based on the maximum permissible lane-changing speed, the minimum safe distance, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle includes: Based on the maximum permissible lane change speed, the minimum safe distance, and the current vehicle's speed, determine the current vehicle's deceleration strategy and lane change speed; The lane-changing trajectory of the current vehicle is determined based on the driving status parameters of the current vehicle and the driving status parameters of the obstacle vehicle.

3. The method according to claim 1, characterized in that, Determining the minimum safe distance between the current vehicle and the obstacle vehicle based on the road surface parameters, the current vehicle's driving status parameters, and the obstacle vehicle's driving status parameters includes: The maximum braking acceleration of the current vehicle is determined based on the road surface adhesion coefficient, which is a road surface parameter. The minimum safe distance between the current vehicle and the obstacle vehicle is determined based on the maximum braking acceleration, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle.

4. The method according to claim 1, characterized in that, The lane-changing decision includes multiple candidate lane-changing decisions, and determining the lane-changing decision for the current vehicle includes: Based on the evaluation model, the evaluation results of the multiple candidate lane change decisions are determined; Based on the evaluation results of the multiple candidate lane change decisions, the target lane change decision is determined from the multiple candidate lane change decisions.

5. The method according to claim 4, characterized in that, The evaluation results for determining the multiple candidate lane change decisions based on the evaluation model include: Based on the artificial potential field method, the safety cost results of the multiple candidate lane change decisions are obtained; Based on the curvature of the multiple lane change trajectories in the multiple candidate lane change decisions, the comfort cost result of the multiple candidate lane change decisions is obtained; The evaluation results of the multiple candidate lane change decisions are determined based on the safety cost results and the comfort cost results.

6. A vehicle decision-making and control system, characterized in that, The system includes a controller and an actuator, the controller storing instructions, and the actuator executing the instructions to cause the system to perform the method as described in any one of claims 1 to 5.

7. A vehicle decision-making and control device, characterized in that, The device includes: The acquisition module is used to acquire the road surface parameters of the current lane, the driving status parameters of the current vehicle, and the driving status parameters of the obstacle vehicle, wherein the obstacle vehicle is a vehicle traveling in the current lane or the target lane. The determination module is configured to: determine the stable lane-changing speed of the current vehicle based on the road surface adhesion coefficient and the maximum road curvature, which are road surface parameters; determine the maximum permissible lane-changing speed of the current vehicle based on the stable lane-changing speed and the speed limit of the current lane; determine the minimum safe distance between the current vehicle and the obstacle vehicle based on the road surface parameters, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle; and determine the lane-changing decision of the current vehicle based on the maximum permissible lane-changing speed, the minimum safe distance, the driving state parameters of the current vehicle, and the driving state parameters of the obstacle vehicle. The control module is used to determine the front wheel steering angle and longitudinal force of the current vehicle based on the lane change decision and a trajectory tracking control model constructed using model predictive control theory, and to determine the active yaw moment of the current vehicle based on a stability control model constructed using sliding mode control; and to control the current vehicle to track the trajectory of the lane change decision and change lanes to the target lane. The determining module is specifically configured to, when the minimum safe distance is less than the distance between the current vehicle and the obstacle vehicle, the distance between the current vehicle and the obstacle vehicle is less than or equal to the decision distance, and the speed of the current vehicle is greater than or equal to the speed of the obstacle vehicle, if the speed of the current vehicle is less than or equal to the maximum permissible lane-changing speed, control the current vehicle to follow the trajectory of the lane-changing decision at its current speed to change lanes; if the speed of the current vehicle is greater than the maximum permissible lane-changing speed, control the current vehicle to decelerate using a deceleration strategy of -0.4 μg until it decelerates to the desired safe distance. The maximum permissible lane change speed is specified, and the vehicle then changes lanes by tracking the trajectory of the lane change decision at the maximum permissible lane change speed. If the current vehicle decelerates at the acceleration of -0.4μg, and the distance between the current vehicle and the obstacle vehicle is between the limit lane change distance and the minimum safe distance, but the vehicle has not decelerated to the maximum permissible lane change speed, the current vehicle is controlled to continue decelerating at the acceleration of -0.8μg until it decelerates to the maximum permissible lane change speed. Then, the vehicle changes lanes by tracking the trajectory of the lane change decision at the maximum permissible lane change speed. Here, μ is the road surface adhesion coefficient, and g is the gravitational acceleration.

8. A vehicle, characterized in that, The vehicle includes the vehicle decision and control system as described in claim 6.

Images