A vehicle lane-changing trajectory planning method, device, equipment and medium

Abstract

The application discloses a vehicle lane-changing trajectory planning method and device, equipment and medium, and relates to the technical field of automatic driving. The method comprises the following steps: determining an initial lane and a target lane of a target vehicle in a lane-changing process, and determining a lane boundary line between the lanes; determining a first state condition of the target vehicle in the initial lane, a second state condition of the target vehicle at the lane boundary line, and a third state condition of the target vehicle in the target lane based on target motion information; determining a preset target model representing a lateral and longitudinal lane-changing trajectory; obtaining a first lane-changing trajectory between the initial lane and the lane boundary line based on the first state condition, the second state condition and the target model; obtaining a second lane-changing trajectory between the lane boundary line and the target lane based on the second state condition, the third state condition and the target model; and connecting the first lane-changing trajectory and the second lane-changing trajectory under a preset constraint condition to obtain a total lane-changing trajectory. The lane-changing trajectory can be more accurately fitted by segmenting the lane-changing trajectory.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a method, apparatus, device, and medium for planning vehicle lane change trajectories. Background Technology

[0002] For the trajectory planning problem of lane changing for autonomous vehicles, existing lane changing trajectory planning algorithms are relatively simple, usually involving curve fitting of the lane changing trajectory using the vehicle's initial and target positions. However, this method is difficult to guarantee the smoothness and accuracy of the lane changing trajectory. Due to the complex and ever-changing road conditions, if autonomous vehicles do not follow a smooth trajectory when changing lanes, it will seriously affect the driver's comfort and easily lead to traffic accidents.

[0003] In summary, how to more accurately fit the lane-changing trajectory during vehicle lane changes is a problem that needs to be solved. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a vehicle lane change trajectory planning method, apparatus, device, and medium, which can more accurately fit the lane change trajectory during the vehicle lane change process. The specific solution is as follows:

[0005] Firstly, this application discloses a vehicle lane-changing trajectory planning method, including:

[0006] Determine the initial lane and target lane of the target vehicle during the lane change process, and determine the lane boundary line between the initial lane and the target lane;

[0007] Based on the target motion information, the first state condition of the target vehicle in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane are determined.

[0008] A pre-set target model is determined to characterize the trajectories of lateral and longitudinal lane changes. Based on the first state condition, the second state condition, and the target model, a first lane change trajectory between the initial lane and the lane boundary line is obtained. Based on the second state condition, the third state condition, and the target model, a second lane change trajectory between the lane boundary line and the target lane is obtained.

[0009] Connect the first lane change trajectory and the second lane change trajectory under preset constraints to obtain the total lane change trajectory of the target vehicle during the lane change process.

[0010] Optionally, the vehicle lane-changing trajectory planning method further includes:

[0011] The initial coordinate position of the target vehicle in the initial lane is determined using a GPS positioning device, and a target coordinate system is established with the initial coordinate position as the origin;

[0012] The horizontal and vertical coordinate positions of the target vehicle in the target coordinate system are determined based on the lateral and longitudinal movement distances of the target vehicle.

[0013] A state condition expression is constructed based on the horizontal and vertical coordinate positions, longitudinal driving speed, longitudinal driving acceleration, and the first and second derivatives of the lateral movement distance with respect to the longitudinal movement distance.

[0014] Optionally, before connecting the first lane change trajectory and the second lane change trajectory under preset constraints, the method further includes...

[0015] A Frenet coordinate system is established with the target vehicle as the origin and the tangent and normal vector directions of the road centerline as mutually perpendicular coordinate axes.

[0016] The coordinate points in the first lane change trajectory and the second lane change trajectory in the target coordinate system are transformed into target coordinate points in the Frenet coordinate system to obtain the first lane change trajectory and the second lane change trajectory after coordinate system transformation.

[0017] Optionally, determining the first state condition of the target vehicle in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane based on target motion information includes:

[0018] Acquire target motion information including vehicle longitudinal speed, lane width, vehicle yaw angle, and preset longitudinal lane change displacement; the preset longitudinal lane change displacement includes a first preset longitudinal lane change displacement between the initial lane and the lane boundary line and a second preset longitudinal lane change displacement between the lane boundary line and the target lane;

[0019] The lane change time is determined by using the vehicle's longitudinal speed and the preset longitudinal lane change displacement, the vehicle's lateral speed is determined by using the vehicle's longitudinal speed and the vehicle's yaw angle, and the lateral acceleration is determined by using the lane change time and the vehicle's lateral speed.

[0020] Substituting the vehicle's longitudinal speed, lane width, preset longitudinal lane change displacement, lane change time, vehicle's lateral speed, and lateral acceleration into the state condition expression, the first state condition of the target vehicle in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane are determined.

[0021] Optionally, the process of acquiring target motion information including vehicle longitudinal speed, lane width, vehicle yaw angle, and preset longitudinal lane change displacement further includes:

[0022] The system uses sensors to obtain the vehicle's longitudinal speed, high-precision maps to obtain the lane width, and electronic stability systems to obtain the vehicle's yaw angle.

[0023] Optionally, the vehicle lane-changing trajectory planning method further includes:

[0024] Several different value conditions are set for the preset longitudinal lane change displacement in the target motion information, and the steps of determining the first state condition of the target vehicle in the initial lane, the second state condition in the lane boundary line and the third state condition in the target lane based on the target motion information are repeatedly executed until a corresponding number of total lane change trajectories corresponding to each value condition are obtained.

[0025] The lateral acceleration in each total lane change trajectory is determined, and the total lane change trajectory corresponding to the minimum lateral acceleration is determined as the optimal lane change trajectory, so that the target vehicle can perform a lane change operation based on the optimal lane change trajectory.

[0026] Optionally, connecting the first lane change trajectory and the second lane change trajectory under preset constraints includes:

[0027] Determine the first derivative value of the first lane change trajectory at the lane boundary line, and determine the second derivative value of the second lane change trajectory at the lane boundary line;

[0028] Connect the first lane change trajectory and the second lane change trajectory under the condition that the first derivative value and the second derivative value are equal.

[0029] Secondly, this application discloses a vehicle lane-changing trajectory planning device, comprising:

[0030] The lane information determination module is used to determine the initial lane and the target lane of the target vehicle during the lane change process, and to determine the lane boundary line between the initial lane and the target lane;

[0031] The state condition determination module is used to determine the first state condition of the target vehicle in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane based on the target motion information.

[0032] The lane change trajectory acquisition module is used to determine a pre-set target model for characterizing the lateral and longitudinal lane change trajectories, and to acquire a first lane change trajectory between the initial lane and the lane boundary line based on the first state condition, the second state condition and the target model, and to acquire a second lane change trajectory between the lane boundary line and the target lane based on the second state condition, the third state condition and the target model.

[0033] The lane change trajectory connection module is used to connect the first lane change trajectory and the second lane change trajectory under preset constraints to obtain the total lane change trajectory of the target vehicle during the lane change process.

[0034] Thirdly, this application discloses an electronic device, including:

[0035] Memory, used to store computer programs;

[0036] A processor is used to execute the computer program to implement the steps of the aforementioned disclosed vehicle lane change trajectory planning method.

[0037] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned disclosed vehicle lane change trajectory planning method.

[0038] As can be seen, this application determines the initial lane and target lane of the target vehicle during the lane change process, and determines the lane boundary line between the initial lane and the target lane; determines the first state condition of the target vehicle in the initial lane, the second state condition in the lane boundary line, and the third state condition in the target lane based on the target motion information; determines a pre-set target model for characterizing the lateral and longitudinal lane change trajectories, and obtains the first lane change trajectory between the initial lane and the lane boundary line based on the first state condition, the second state condition, and the target model, and obtains the second lane change trajectory between the lane boundary line and the target lane based on the second state condition, the third state condition, and the target model; and connects the first lane change trajectory and the second lane change trajectory under preset constraints to obtain the total lane change trajectory of the target vehicle during the lane change process. Therefore, this application first determines the initial lane and target lane during the lane-changing process, and then determines the lane boundary line between the initial lane and the target lane. Next, based on the target motion information, it determines the first, second, and third state conditions corresponding to the target vehicle in the initial lane, lane boundary line, and target lane, respectively. Then, it determines a pre-set target model to characterize the lateral and longitudinal lane-changing trajectories, and uses the first and second state conditions and the target model to obtain the first lane-changing trajectory between the initial lane and the lane boundary line. It also obtains the second lane-changing trajectory between the lane boundary line and the target lane based on the second and third state conditions and the target model. Finally, under preset constraints, it connects the first and second lane-changing trajectories to obtain the total lane-changing trajectory during the lane-changing process. In other words, this application divides the lane-changing process into two stages: one stage is the lane-changing process between the initial lane and the lane boundary line, and the other stage is the lane-changing process between the lane boundary line and the target lane. It then uses the corresponding state conditions and the pre-set target model to fit and solve for the lane-changing trajectories corresponding to the two stages, and finally connects the lane-changing trajectories obtained from the two stages under preset constraints to obtain the total lane-changing trajectory. By segmenting the lane change trajectory into segments, the lane change trajectory can be fitted more accurately. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0040] Figure 1 This is a flowchart of a vehicle lane change trajectory planning method disclosed in this application;

[0041] Figure 2 This application discloses a specific method for planning vehicle lane change trajectories.

[0042] Figure 3 This is a flowchart of another specific vehicle lane change trajectory planning method disclosed in this application;

[0043] Figure 4 This is a schematic diagram of the structure of a vehicle lane change trajectory planning device disclosed in this application;

[0044] Figure 5 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0046] For the trajectory planning problem of lane changing for autonomous vehicles, existing lane changing trajectory planning algorithms are relatively simple, usually involving curve fitting of the lane changing trajectory using the vehicle's initial and target positions. However, this method struggles to guarantee the smoothness and accuracy of the lane changing trajectory. Due to the complex and ever-changing road conditions, if an autonomous vehicle does not follow a smooth trajectory when changing lanes, it will severely affect driver comfort and easily lead to traffic accidents. Therefore, this application discloses a vehicle lane changing trajectory planning method, apparatus, device, and medium, which can more accurately fit the lane changing trajectory during the vehicle's lane changing process.

[0047] See Figure 1 As shown in the figure, this application discloses a vehicle lane-changing trajectory planning method, which includes:

[0048] Step S11: Determine the initial lane and target lane of the target vehicle during the lane change process, and determine the lane boundary line between the initial lane and the target lane.

[0049] In this embodiment, the initial lane and the target lane of the target vehicle during the lane change process are first determined. The initial lane is the lane where the target vehicle is currently located, and the target lane is the lane that the target vehicle needs to reach after changing lanes. Then, the lane boundary line between the initial lane and the target lane is determined.

[0050] Step S12: Based on the target motion information, determine the first state condition of the target vehicle in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane.

[0051] In this embodiment, based on the target motion information, the first state condition, the second state condition, and the third state condition corresponding to the target vehicle in the initial lane, the lane boundary line, and the target lane, respectively, are determined. The target motion information is related to the target vehicle's motion state and lane parameters; this information can be directly obtained through relevant detection equipment or has been pre-set with specific values.

[0052] Step S13: Determine a pre-set polynomial function to characterize the trajectories of lateral and longitudinal lane changes, and obtain the first lane change trajectory between the initial lane and the lane boundary line based on the first state condition, the second state condition and the target model, and obtain the second lane change trajectory between the lane boundary line and the target lane based on the second state condition, the third state condition and the target model.

[0053] In this embodiment, a pre-set target model is determined to characterize the lateral and longitudinal lane change trajectories. The target model is in the form of a polynomial function. In a specific implementation, this polynomial function is a fifth-order polynomial function. The lateral lane change trajectory is a fifth-order polynomial with respect to the lane change time; the longitudinal lane change trajectory is a fifth-order polynomial with respect to the lateral lane change trajectory. The specific expressions are as follows:

[0054]

[0055] Where t represents time, x and y represent the longitudinal and lateral movement distances respectively, and a i and b i Let i represent the coefficients, where i = 0, 1, 2, 3, 4, 5.

[0056] Then, the polynomial function is solved using the first and second state conditions to obtain the first lane change trajectory between the initial lane and the lane boundary line, and the polynomial function is solved based on the second and third state conditions to obtain the second lane change trajectory between the lane boundary line and the target lane.

[0057] Step S14: Connect the first lane change trajectory and the second lane change trajectory under preset constraints to obtain the total lane change trajectory of the target vehicle during the lane change process.

[0058] In this embodiment, by connecting the first lane change trajectory and the second lane change trajectory under preset constraints, the total lane change trajectory of the target vehicle during the lane change process can be obtained.

[0059] As can be seen, this application determines the initial lane and target lane of the target vehicle during the lane change process, and determines the lane boundary line between the initial lane and the target lane; determines the first state condition of the target vehicle in the initial lane, the second state condition in the lane boundary line, and the third state condition in the target lane based on the target motion information; determines a pre-set target model for characterizing the lateral and longitudinal lane change trajectories, and obtains the first lane change trajectory between the initial lane and the lane boundary line based on the first state condition, the second state condition, and the target model, and obtains the second lane change trajectory between the lane boundary line and the target lane based on the second state condition, the third state condition, and the target model; and connects the first lane change trajectory and the second lane change trajectory under preset constraints to obtain the total lane change trajectory of the target vehicle during the lane change process. Therefore, this application first determines the initial lane and target lane during the lane-changing process, and then determines the lane boundary line between the initial lane and the target lane. Next, based on the target motion information, it determines the first, second, and third state conditions corresponding to the target vehicle in the initial lane, lane boundary line, and target lane, respectively. Then, it determines a pre-set target model to characterize the lateral and longitudinal lane-changing trajectories, and uses the first and second state conditions and the target model to obtain the first lane-changing trajectory between the initial lane and the lane boundary line. It also obtains the second lane-changing trajectory between the lane boundary line and the target lane based on the second and third state conditions and the target model. Finally, under preset constraints, it connects the first and second lane-changing trajectories to obtain the total lane-changing trajectory during the lane-changing process. In other words, this application divides the lane-changing process into two stages: one stage is the lane-changing process between the initial lane and the lane boundary line, and the other stage is the lane-changing process between the lane boundary line and the target lane. It then uses the corresponding state conditions and the pre-set target model to fit and solve for the lane-changing trajectories corresponding to the two stages, and finally connects the lane-changing trajectories obtained from the two stages under preset constraints to obtain the total lane-changing trajectory. By segmenting the lane change trajectory into segments, the lane change trajectory can be fitted more accurately.

[0060] See Figure 2 As shown, this application discloses a specific method for vehicle lane-changing trajectory planning. Compared to the previous embodiment, this embodiment further explains and optimizes the technical solution. Specifically, it includes:

[0061] Step S21: Determine the initial lane and target lane of the target vehicle during the lane change process, and determine the lane boundary line between the initial lane and the target lane.

[0062] Step S22: Obtain target motion information including vehicle longitudinal speed, lane width, vehicle yaw angle and preset longitudinal lane change displacement; the preset longitudinal lane change displacement includes a first preset longitudinal lane change displacement between the initial lane and the lane boundary line and a second preset longitudinal lane change displacement between the lane boundary line and the target lane.

[0063] In this embodiment, the target motion information may include, but is not limited to, vehicle longitudinal speed, lane width, vehicle yaw angle, and preset longitudinal lane change displacement. The preset longitudinal lane change displacement includes a first preset longitudinal lane change displacement l1 between the initial lane and the lane boundary line, and a second preset longitudinal lane change displacement l2 between the lane boundary line and the target lane. It can be understood that this embodiment divides the lane change process into two stages. In the first stage, the target vehicle changes lanes from the initial lane to the lane boundary line with a corresponding first preset longitudinal lane change displacement l1; in the second stage, the target vehicle changes lanes from the lane boundary line to the target lane with a corresponding second preset longitudinal lane change displacement l2. The preset longitudinal lane change displacement can be preset to a specific value.

[0064] Furthermore, the process of acquiring target motion information, including vehicle longitudinal speed, lane width, vehicle yaw angle, and preset longitudinal lane change displacement, further includes: acquiring vehicle longitudinal speed using sensors, acquiring lane width using a high-precision map, and acquiring vehicle yaw angle using an electronic stability program (ESP). That is, among the parameters mentioned above, the preset longitudinal lane change displacement is a pre-set value, while the other parameters need to be acquired through relevant detection equipment. Specifically, the vehicle longitudinal speed *v* is acquired using sensor equipment, the lane width *width* is acquired using a high-precision map, and the vehicle yaw angle *θ* can be obtained from the ESP, with the average value calculated at different vehicle speeds through real-vehicle testing.

[0065] Step S23: Determine the lane change time using the vehicle's longitudinal speed and the preset longitudinal lane change displacement, determine the vehicle's lateral speed using the vehicle's longitudinal speed and the vehicle's yaw angle, and determine the lateral acceleration using the lane change time and the vehicle's lateral speed.

[0066] In this embodiment, the lane-change time is determined using the vehicle's longitudinal speed and a preset longitudinal lane-change displacement. It can be understood that in this embodiment, the vehicle's longitudinal speed is assumed to remain constant, meaning the vehicle moves at a uniform speed longitudinally. Therefore, the lane-change time can be determined based on the ratio of the preset longitudinal lane-change displacement to the vehicle's longitudinal speed. Specifically, the lane-change time Δt1 required for the target vehicle to change lanes from the initial lane to the lane boundary line can be determined based on the first preset longitudinal lane-change displacement l1 and the vehicle's longitudinal speed v. The lane-change time Δt2 required for the target vehicle to change lanes from the lane boundary line to the target lane can be determined based on the second preset longitudinal lane-change displacement and the vehicle's longitudinal speed. Additionally, the vehicle's lateral speed v... y The yaw rate can be calculated using the vehicle's longitudinal velocity v and yaw angle θ. Since the target vehicle's initial velocity in the lateral direction is 0, let the lateral acceleration be a. y The variable speed motion, then using the lateral travel speed v y The lateral acceleration a can be determined by the lane change time Δt1. y .

[0067] Step S24: Substitute the vehicle's longitudinal speed, lane width, preset longitudinal lane change displacement, lane change time, vehicle's lateral speed, and lateral acceleration into the state condition expression to determine the target vehicle's first state condition in the initial lane, second state condition at the lane boundary line, and third state condition in the target lane.

[0068] In this embodiment, it should be noted that the above method further includes: determining the initial coordinate position of the target vehicle in the initial lane using a GPS positioning device, and establishing a target coordinate system with the initial coordinate position as the origin; determining the horizontal and vertical coordinate positions of the target vehicle in the target coordinate system based on the lateral and longitudinal movement distances of the target vehicle; and constructing a state condition expression based on the horizontal and vertical coordinate positions, longitudinal driving speed, longitudinal driving acceleration, and the first and second derivatives of the lateral movement distance with respect to the longitudinal movement distance. In this embodiment, it is necessary to use a GPS positioning device to determine the initial coordinate position of the target vehicle in the initial lane, and establish a target coordinate system with the initial coordinate position as the origin, specifically a Cartesian coordinate system. In this way, the horizontal and vertical coordinate positions of the target vehicle in the coordinate system can be determined based on the lateral and longitudinal movement distances of the target vehicle. Let's assume the coordinate positions are denoted as (longitudinal movement distance, lateral movement distance). Furthermore... It should be noted that in this embodiment, the initial coordinate position is set at the center line of the initial lane, and the target coordinate position after lane change is also set at the center line of the target lane. Therefore, the initial coordinate position of the target vehicle is (0,0); the coordinate position on the lane boundary line is (l1, width / 2); and the target coordinate position is (l1+l2, width).

[0069] In this embodiment, the state condition expression S for each position is constructed based on the horizontal and vertical coordinate positions, the longitudinal driving speed, the longitudinal driving acceleration, and the first and second derivatives of the lateral movement distance with respect to the longitudinal movement distance. The specific state condition expression is as follows:

[0070]

[0071] Where t represents the lane change time; x(t) is the vertical axis, i.e., the longitudinal movement distance; This is the first derivative of the longitudinal distance with respect to the lane change time, i.e., the longitudinal driving speed; y(x) is the second derivative of the longitudinal distance with respect to the lane change time, i.e., the longitudinal acceleration; y(x) is the abscissa, i.e., the lateral movement distance; y′(x) is the first derivative of the lateral movement distance with respect to the longitudinal movement distance, representing the lateral acceleration; y″(x) is the second derivative of the lateral movement distance with respect to the longitudinal movement distance, i.e., the lateral acceleration.

[0072] Furthermore, the vehicle's longitudinal speed, lane width, preset longitudinal lane change displacement, lane change time, vehicle's lateral speed, and lateral acceleration are substituted into the state condition expression to determine the target vehicle's first state condition in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane, respectively.

[0073] Specifically, the first state condition S1 of the target vehicle in the initial lane is:

[0074]

[0075] It is understandable that, based on the above, the initial coordinate position of the target vehicle is (0,0), meaning that both the longitudinal and lateral movement distances are 0; the longitudinal speed is v; since the longitudinal speed of the vehicle is set to remain constant, the longitudinal acceleration is 0; and since no lane change operation has been performed in the initial lane, the lateral speed and lateral acceleration are also 0.

[0076] The second state condition S2 for the target vehicle at the lane boundary line is:

[0077]

[0078] As can be understood from the foregoing, the target vehicle's coordinates on the lane boundary are (l1, width / 2), meaning its longitudinal movement distance is l1 and width / 2; its longitudinal speed is v; its longitudinal acceleration is 0; and it already has a lateral speed v. y Lateral acceleration a y .

[0079] The second state condition S3 for the target vehicle in the target lane is:

[0080]

[0081] As can be understood from the foregoing, the target vehicle's target coordinates are (l1+l2, width), meaning the longitudinal movement distance is l1+l2 and the longitudinal movement distance is width; the longitudinal speed is v; the longitudinal acceleration is 0; and the lateral speed is v. y +a y Δt2; Lateral acceleration remains a y .

[0082] Step S25: Determine a pre-set target model for characterizing the trajectories of lateral and longitudinal lane changes, and obtain the first lane change trajectory between the initial lane and the lane boundary line based on the first state condition, the second state condition and the target model, and obtain the second lane change trajectory between the lane boundary line and the target lane based on the second state condition, the third state condition and the target model.

[0083] In this embodiment, the target model can specifically be a fifth-order polynomial function. After determining the pre-set fifth-order polynomial function representing the lateral and longitudinal lane change trajectories, the first and second state conditions are substituted into the polynomial function to solve for the first lane change trajectory between the initial lane and the lane boundary line. Similarly, the second and third state conditions are substituted into the polynomial function to solve for the second lane change trajectory between the lane boundary line and the target lane. Specifically, x(t) is established at each stage based on the corresponding two state conditions. The relationship between the lane change time t and the equations relating y(x), y′(x), y″(x) and x is established. By solving these equations simultaneously, the coefficients of the fifth-degree polynomial function are obtained, thus yielding the corresponding lane change trajectory expression.

[0084] Step S26: Connect the first lane change trajectory and the second lane change trajectory under preset constraints to obtain the total lane change trajectory of the target vehicle during the lane change process.

[0085] In this embodiment, before connecting the first lane change trajectory and the second lane change trajectory under preset constraints, the method further includes establishing a Frenet coordinate system with the target vehicle as the origin and the tangent vector direction and normal vector direction of the road centerline as mutually perpendicular coordinate axes; transforming the coordinate points in the first lane change trajectory and the second lane change trajectory in the target coordinate system into target coordinate points in the Frenet coordinate system to obtain the first lane change trajectory and the second lane change trajectory after coordinate system transformation. That is, in this embodiment, it is necessary to transform the coordinate points (x, y) in the first lane change trajectory and the second lane change trajectory in the Cartesian coordinate system into target coordinate points (s, d) in the Frenet coordinate system to obtain the first lane change trajectory and the second lane change trajectory in the Frenet coordinate system, i.e., obtaining the Frenet trajectory lines of the two stages, denoted as T1 = Q. i (d), T2=P i (d); i = 1, ..., n.

[0086] Under preset constraints, the first and second lane change trajectories in the Frenet coordinate system are connected to obtain the total lane change trajectory.

[0087] For a more detailed description of the process of step S21, please refer to the relevant content disclosed in the foregoing embodiments, which will not be repeated here.

[0088] As can be seen, this embodiment determines parameters such as lane change time, lateral speed, and lateral acceleration based on the acquired target motion information, including vehicle longitudinal speed, lane width, vehicle yaw angle, and preset longitudinal lane change displacement. These parameters are then substituted into the state condition expression to determine the first state condition of the target vehicle in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane. Polynomial functions are then solved in each of the two stages based on the corresponding state conditions to obtain the first lane change trajectory in the first stage and the second lane change trajectory in the second stage. The coordinates of the lane change trajectories are then transformed from the Cartesian coordinate system to the Frenet coordinate system, and the first and second lane change trajectories in the Frenet coordinate system are connected under preset constraints to obtain the total lane change trajectory. By determining the state conditions at different locations and then using the corresponding state conditions to fit and solve the polynomial function in stages to obtain the corresponding lane change trajectory, the accuracy of trajectory fitting is improved through segmented planning of the lane change trajectory.

[0089] See Figure 3 As shown in the figure, this application discloses a vehicle lane-changing trajectory planning method, which includes:

[0090] Step S31: Determine the initial lane and target lane of the target vehicle during the lane change process, and determine the lane boundary line between the initial lane and the target lane.

[0091] Step S32: Based on the target motion information, determine the first state condition of the target vehicle in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane.

[0092] Step S33: Determine a pre-set target model for characterizing the trajectories of lateral and longitudinal lane changes, and obtain the first lane change trajectory between the initial lane and the lane boundary line based on the first state condition, the second state condition and the target model, and obtain the second lane change trajectory between the lane boundary line and the target lane based on the second state condition, the third state condition and the target model.

[0093] Step S34: Determine the first derivative value of the first lane change trajectory at the lane boundary line, and determine the second derivative value of the second lane change trajectory at the lane boundary line; connect the first lane change trajectory and the second lane change trajectory under the condition that the first derivative value and the second derivative value are equal, so as to obtain the total lane change trajectory of the target vehicle during the lane change process.

[0094] In this embodiment, the preset constraint condition can be that the derivative value of the right endpoint of the first lane change trajectory T1 is equal to the derivative value of the left endpoint of the second lane change trajectory T2. The intersection point of the two lane change trajectories is located at the lane boundary line. That is, it is necessary to determine the first derivative value of the first lane change trajectory at the lane boundary line and the second derivative value of the second lane change trajectory at the lane boundary line. The first lane change trajectory and the second lane change trajectory are connected while keeping the first derivative value and the second derivative value equal, so as to obtain the total lane change trajectory of the target vehicle during the lane change process. By keeping the derivative values ​​equal, the smoothness of the lane change trajectory can be improved.

[0095] Step S35: Set several different value conditions for the preset longitudinal lane change displacement in the target motion information, and repeatedly execute the step of determining the first state condition of the target vehicle in the initial lane, the second state condition in the lane boundary line, and the third state condition in the target lane based on the target motion information, until a corresponding number of total lane change trajectories corresponding to each value condition are obtained.

[0096] In this embodiment, as disclosed above, the preset longitudinal lane change displacement in the target motion information is determined by pre-setting its value. If the preset longitudinal lane change displacement value is different, the corresponding lane change time and lateral acceleration will change accordingly, and the state conditions at each position will also be different. In this embodiment, by setting several different value conditions for the preset longitudinal lane change displacement, and repeatedly executing the steps of determining the first state condition of the target vehicle in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane based on the target motion information, a corresponding number of total lane change trajectories corresponding to each value condition are obtained.

[0097] Step S36: Determine the lateral acceleration in each of the total lane change trajectories, and determine the total lane change trajectory corresponding to the minimum lateral acceleration as the optimal lane change trajectory, so that the target vehicle can perform a lane change operation based on the optimal lane change trajectory.

[0098] In this embodiment, after obtaining multiple total lane change trajectories by taking different values ​​for the preset longitudinal lane change displacement, the lateral acceleration of each total lane change trajectory is determined, and the total lane change trajectory corresponding to the minimum lateral acceleration is determined as the optimal lane change trajectory. In other words, this embodiment samples multiple total lane change trajectories and selects an optimal trajectory line with the minimum lateral acceleration as the target, so that the target vehicle can perform lane change operations based on this optimal trajectory. In this way, by using the minimum lateral acceleration as the optimization target in selecting lane change trajectory lines, the smoothness of the lane change trajectory is ensured.

[0099] For more detailed processing procedures regarding steps S31, S32, and S33, please refer to the corresponding content disclosed in the foregoing embodiments, which will not be repeated here.

[0100] As can be seen, this embodiment connects the first lane change trajectory and the second lane change trajectory while maintaining the derivative value of the right endpoint of the first lane change trajectory T1 equal to the derivative value of the left endpoint of the second lane change trajectory T2, thereby improving the smoothness of the lane change trajectory. Furthermore, this embodiment sets different value conditions for the preset longitudinal lane change displacement in the target motion information; that is, different values ​​can obtain multiple total lane change trajectories. Then, using the minimum lateral acceleration as the optimization objective, the total lane change trajectory corresponding to the minimum lateral acceleration is selected from the multiple total lane change trajectories as the optimal lane change trajectory, so that the target vehicle can perform lane change operations based on this optimal lane change trajectory. By considering the minimum lateral acceleration as the optimization objective, the smoothness of the lane change trajectory is guaranteed.

[0101] See Figure 4 As shown in the figure, this application discloses a vehicle lane-changing trajectory planning device, which includes:

[0102] Lane information determination module 11 is used to determine the initial lane and target lane of the target vehicle during the lane change process, and to determine the lane boundary line between the initial lane and the target lane;

[0103] The state condition determination module 12 is used to determine the first state condition of the target vehicle in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane based on the target motion information.

[0104] The lane change trajectory acquisition module 13 is used to determine a pre-set polynomial function for characterizing the lateral and longitudinal lane change trajectories, and to acquire a first lane change trajectory between the initial lane and the lane boundary line based on the first state condition, the second state condition and the target model, and to acquire a second lane change trajectory between the lane boundary line and the target lane based on the second state condition, the third state condition and the target model.

[0105] The lane change trajectory connection module 14 is used to connect the first lane change trajectory and the second lane change trajectory under preset constraints to obtain the total lane change trajectory of the target vehicle during the lane change process.

[0106] As can be seen, this application determines the initial lane and target lane of the target vehicle during the lane change process, and determines the lane boundary line between the initial lane and the target lane; determines the first state condition of the target vehicle in the initial lane, the second state condition in the lane boundary line, and the third state condition in the target lane based on the target motion information; determines a pre-set polynomial function to characterize the lateral and longitudinal lane change trajectories, and obtains the first lane change trajectory between the initial lane and the lane boundary line based on the first state condition, the second state condition, and the target model, and obtains the second lane change trajectory between the lane boundary line and the target lane based on the second state condition, the third state condition, and the target model; and connects the first lane change trajectory and the second lane change trajectory under preset constraints to obtain the total lane change trajectory of the target vehicle during the lane change process. Therefore, this application first determines the initial lane and target lane during the lane-changing process, and then determines the lane boundary line between the initial lane and the target lane. Next, based on the target motion information, it determines the first, second, and third state conditions corresponding to the target vehicle in the initial lane, lane boundary line, and target lane, respectively. Then, it determines a pre-set target model to characterize the lateral and longitudinal lane-changing trajectories, and uses the first and second state conditions and the target model to obtain the first lane-changing trajectory between the initial lane and the lane boundary line. It also obtains the second lane-changing trajectory between the lane boundary line and the target lane based on the second and third state conditions and the target model. Finally, under preset constraints, it connects the first and second lane-changing trajectories to obtain the total lane-changing trajectory during the lane-changing process. In other words, this application divides the lane-changing process into two stages: one stage is the lane-changing process between the initial lane and the lane boundary line, and the other stage is the lane-changing process between the lane boundary line and the target lane. It then uses the corresponding state conditions and the pre-set target model to fit and solve for the lane-changing trajectories corresponding to the two stages, and finally connects the lane-changing trajectories obtained from the two stages under preset constraints to obtain the total lane-changing trajectory. By segmenting the lane change trajectory into segments, the lane change trajectory can be fitted more accurately.

[0107] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the vehicle lane change trajectory planning method performed by the electronic device disclosed in any of the foregoing embodiments.

[0108] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0109] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0110] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored on it include operating system 221, computer program 222 and data 223, etc., and the storage method can be temporary storage or permanent storage.

[0111] The operating system 221 manages and controls the various hardware devices and computer programs 222 on the electronic device 20 to enable the processor 21 to perform calculations and processing on the massive amounts of data 223 in the memory 22. The operating system can be Windows, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the vehicle lane-changing trajectory planning method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the electronic device from external devices, as well as data collected by its own input / output interface 25.

[0112] Furthermore, embodiments of this application also disclose a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, it implements the method steps performed during the vehicle lane change trajectory planning process disclosed in any of the foregoing embodiments.

[0113] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0114] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0115] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0116] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0117] The present invention provides a detailed description of a vehicle lane change trajectory planning method, apparatus, device, and storage medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for planning vehicle lane-changing trajectories, characterized in that, include: Determine the initial lane and target lane of the target vehicle during the lane change process, and determine the lane boundary line between the initial lane and the target lane; Based on the target motion information, the first state condition of the target vehicle in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane are determined. A pre-set target model is determined to characterize the trajectories of lateral and longitudinal lane changes. Based on the first state condition, the second state condition, and the target model, a first lane change trajectory between the initial lane and the lane boundary line is obtained. Based on the second state condition, the third state condition, and the target model, a second lane change trajectory between the lane boundary line and the target lane is obtained. Under preset constraints, the first lane change trajectory and the second lane change trajectory are connected to obtain the total lane change trajectory of the target vehicle during the lane change process; The method further includes: The initial coordinate position of the target vehicle in the initial lane is determined using a GPS positioning device, and a target coordinate system is established with the initial coordinate position as the origin; The horizontal and vertical coordinate positions of the target vehicle in the target coordinate system are determined based on the lateral and longitudinal movement distances of the target vehicle. A state condition expression is constructed based on the horizontal and vertical coordinate positions, the longitudinal driving speed, the longitudinal driving acceleration, and the first and second derivatives of the lateral movement distance with respect to the longitudinal movement distance; The determination of the target vehicle's first state condition in the initial lane, second state condition at the lane boundary line, and third state condition in the target lane based on target motion information includes: Acquire target motion information including vehicle longitudinal speed, lane width, vehicle yaw angle, and preset longitudinal lane change displacement; the preset longitudinal lane change displacement includes a first preset longitudinal lane change displacement between the initial lane and the lane boundary line and a second preset longitudinal lane change displacement between the lane boundary line and the target lane; The lane change time is determined by using the vehicle's longitudinal speed and the preset longitudinal lane change displacement, the vehicle's lateral speed is determined by using the vehicle's longitudinal speed and the vehicle's yaw angle, and the lateral acceleration is determined by using the lane change time and the vehicle's lateral speed. Substituting the vehicle's longitudinal speed, lane width, preset longitudinal lane change displacement, lane change time, vehicle's lateral speed, and lateral acceleration into the state condition expression, the first state condition of the target vehicle in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane are determined.

2. The vehicle lane change trajectory planning method according to claim 1, characterized in that, Before connecting the first lane change trajectory and the second lane change trajectory under preset constraints, the process also includes... A Frenet coordinate system is established with the target vehicle as the origin and the tangent and normal vector directions of the road centerline as mutually perpendicular coordinate axes. The coordinate points in the first lane change trajectory and the second lane change trajectory in the target coordinate system are transformed into target coordinate points in the Frenet coordinate system to obtain the first lane change trajectory and the second lane change trajectory after coordinate system transformation.

3. The vehicle lane-changing trajectory planning method according to claim 1, characterized in that, The process of acquiring target motion information, including vehicle longitudinal speed, lane width, vehicle yaw angle, and preset longitudinal lane change displacement, also includes: The system uses sensors to obtain the vehicle's longitudinal speed, high-precision maps to obtain the lane width, and electronic stability systems to obtain the vehicle's yaw angle.

4. The vehicle lane change trajectory planning method according to claim 1, characterized in that, Also includes: Several different value conditions are set for the preset longitudinal lane change displacement in the target motion information, and the steps of determining the first state condition of the target vehicle in the initial lane, the second state condition in the lane boundary line and the third state condition in the target lane based on the target motion information are repeatedly executed until a corresponding number of total lane change trajectories corresponding to each value condition are obtained. The lateral acceleration in each total lane change trajectory is determined, and the total lane change trajectory corresponding to the minimum lateral acceleration is determined as the optimal lane change trajectory, so that the target vehicle can perform a lane change operation based on the optimal lane change trajectory.

5. The vehicle lane change trajectory planning method according to any one of claims 1 to 4, characterized in that, Connecting the first lane change trajectory and the second lane change trajectory under preset constraints includes: Determine the first derivative value of the first lane change trajectory at the lane boundary line, and determine the second derivative value of the second lane change trajectory at the lane boundary line; Connect the first lane change trajectory and the second lane change trajectory under the condition that the first derivative value and the second derivative value are equal.

6. A vehicle lane-changing trajectory planning device, characterized in that, include: The lane information determination module is used to determine the initial lane and the target lane of the target vehicle during the lane change process, and to determine the lane boundary line between the initial lane and the target lane; The state condition determination module is used to determine the first state condition of the target vehicle in the initial lane, the second state condition at the lane boundary line, and the third state condition in the target lane based on the target motion information. The lane change trajectory acquisition module is used to determine a pre-set target model for characterizing the lateral and longitudinal lane change trajectories, and to acquire a first lane change trajectory between the initial lane and the lane boundary line based on the first state condition, the second state condition and the target model, and to acquire a second lane change trajectory between the lane boundary line and the target lane based on the second state condition, the third state condition and the target model. The lane change trajectory connection module is used to connect the first lane change trajectory and the second lane change trajectory under preset constraints to obtain the total lane change trajectory of the target vehicle during the lane change process. The device is further configured to: determine the initial coordinate position of the target vehicle in the initial lane using a GPS positioning device, and establish a target coordinate system with the initial coordinate position as the origin; and determine the horizontal and vertical coordinate positions of the target vehicle in the target coordinate system based on the lateral and longitudinal movement distances of the target vehicle. A state condition expression is constructed based on the horizontal and vertical coordinate positions, the longitudinal driving speed, the longitudinal driving acceleration, and the first and second derivatives of the lateral movement distance with respect to the longitudinal movement distance; The state condition determination module is specifically used to acquire target motion information including vehicle longitudinal speed, lane width, vehicle yaw angle, and preset longitudinal lane change displacement; the preset longitudinal lane change displacement includes a first preset longitudinal lane change displacement between the initial lane and the lane boundary line and a second preset longitudinal lane change displacement between the lane boundary line and the target lane; the lane change time is determined using the vehicle longitudinal speed and the preset longitudinal lane change displacement, the vehicle lateral speed is determined using the vehicle longitudinal speed and the vehicle yaw angle, and the lateral acceleration is determined using the lane change time and the vehicle lateral speed; the vehicle longitudinal speed, lane width, preset longitudinal lane change displacement, lane change time, vehicle lateral speed, and lateral acceleration are substituted into the state condition expression to determine the first state condition of the target vehicle in the initial lane, the second state condition in the lane boundary line, and the third state condition in the target lane.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor is configured to execute the computer program to implement the steps of the vehicle lane change trajectory planning method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the vehicle lane change trajectory planning method as described in any one of claims 1 to 5.

Images