Method, device and storage medium for controlling vehicle lane change

Abstract

The present application discloses a method, device and storage medium for controlling vehicle lane changes, which are applied to autonomous vehicles. The method includes: receiving a lane change signal; obtaining target lane position information; determining the initial lane change path of the autonomous vehicle based on the target lane position information; determining the kinematic constraints of the autonomous vehicle; determining a target optimization function based on the initial lane change path and the kinematic constraints; determining the target lane change path of the autonomous vehicle through the target optimization function; generating corresponding control decisions based on the target lane change path to control the driving of the autonomous vehicle. The present application can further generate the target lane change path of the autonomous vehicle through the kinematic constraints of the autonomous vehicle, taking into account the globality of the planned path, which is conducive to planning a reasonable path more efficiently.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, device, and storage medium for controlling vehicle lane changes. Background Art

[0002] As people's living standards continue to improve, the number of cars in China is increasing year by year, and with it, the number of traffic accidents. This is particularly true of accidents on highways, where high speeds often increase the severity of accidents. Data shows that illegal lane changes are one of the leading causes of highway accidents. Compared to traditional human drivers, autonomous driving systems have longer perception ranges and faster reaction times, making them better able to handle various emergencies. Against this backdrop, autonomous driving systems have become a research hotspot for major companies, universities, and research institutions in recent years, and have yielded fruitful results.

[0003] Prior art methods for generating lane change trajectories for autonomous vehicles generally first obtain the vehicle's current driving parameters, then determine the lane change time for each preset lane change phase based on the current driving parameters and a preset algorithm. The vehicle's acceleration and steering angle during each preset lane change phase are then determined based on the trajectory algorithm corresponding to each preset lane change phase, where the vehicle's acceleration and steering angle changes are not simultaneously non-zero. The vehicle's lane change trajectory is then generated based on the lane change time, speed, and steering angle during each preset lane change phase. The main drawback of this method is that it fails to consider the overall trajectory, often resulting in unusual lane change paths that are inconsistent with human driving habits and offer poor comfort. Furthermore, it relies on pre-set vehicle values. If these values ​​are not set appropriately, the resulting planned trajectory can be illogical or even unsafe, and its applicability is limited.

[0004] Therefore, the method for controlling vehicle lane changes used in the prior art has unreasonable path planning, a small scope of application, and potential driving safety hazards. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a method, device and storage medium for controlling vehicle lane changes, so as to solve the problems of unreasonable path planning, small scope of application and potential driving safety hazards in the methods used in the prior art for controlling vehicle lane changes.

[0006] To achieve the above objectives, the present application provides, in a first aspect, a method for controlling vehicle lane changes, which is applied to an autonomous driving vehicle. The method comprises:

[0007] receiving lane change signals;

[0008] Get the target lane position information;

[0009] Determine the initial lane change path of the autonomous vehicle based on the target lane position information;

[0010] Determine the kinematic constraints of an autonomous vehicle;

[0011] Determine the target optimization function based on the initial lane change path and kinematic constraints;

[0012] Determine the target lane change path of the autonomous driving vehicle through the target optimization function;

[0013] Generate corresponding control decisions based on the target lane change path to control the driving of the autonomous driving vehicle.

[0014] In this embodiment of the present application, the kinematic constraints of the autonomous driving vehicle include:

[0015] Speed ​​constraints, acceleration constraints, jerk constraints, minimum turning radius constraints, lane boundary distance constraints, and minimum time constraints.

[0016] In the embodiment of the present application, the target optimization function satisfies formula (1) and formula (2):

[0017]

[0018]

[0019] in, is the target lane change path, is the target optimization function, is the speed constraint, a k is the acceleration constraint, is the jerk constraint, ρ k is the minimum turning radius constraint, o k is the lane boundary distance constraint, ΔT k 2 is the shortest time constraint, and a, b, c, d, e and f are weighting coefficients.

[0020] In the embodiment of the present application, the speed constraint satisfies formula (3):

[0021]

[0022] in, is the acceleration constraint, s k is the position information of the autonomous driving vehicle at point k, v max The maximum speed of the autonomous vehicle, v k is the speed of the autonomous vehicle at point k, ω max is the maximum acceleration of the autonomous vehicle, ω k is the angular velocity of the autonomous vehicle at point k, ΔTk The time difference between the autonomous vehicle at point k and point k+1, T is the running time of the autonomous vehicle;

[0023] The acceleration constraint satisfies formula (4):

[0024] a k (s k+2 ,s k+1 ,s k ,ΔT k+1 ,ΔT k )=a max -|a k |; (4)

[0025] Among them, a k is the acceleration constraint, a max is the maximum acceleration of the autonomous vehicle, a k is the acceleration of the autonomous vehicle at point k, ΔT k+1 is the time difference between the autonomous driving vehicle at point k+1 and point k+2;

[0026] The jerk constraint satisfies formula (5):

[0027]

[0028] in, is the jerk constraint, j max is the maximum acceleration of the autonomous vehicle, j k is the acceleration of the autonomous vehicle at point k.

[0029] In an embodiment of the present application, determining the target optimization function based on the initial lane change path and the kinematic constraints includes:

[0030] The initial lane change path is converted into multiple discrete path points with pose information to obtain the pose sequence corresponding to the initial lane change path;

[0031] Determine the time series corresponding to the pose sequence;

[0032] Merge the pose sequence and time series to obtain the function to be optimized;

[0033] The target optimization function is determined based on the function to be optimized and the kinematic constraints.

[0034] In an embodiment of the present application, determining the kinematic constraints of the autonomous driving vehicle includes:

[0035] Collect obstacle information around the autonomous vehicle;

[0036] The lane boundary constraints are determined based on the pose sequence and obstacle information corresponding to the initial lane change path.

[0037] In an embodiment of the present application, determining the kinematic constraints of the autonomous driving vehicle includes:

[0038] Obtaining geometric characteristic parameters of the autonomous driving vehicle;

[0039] Construct a kinematic model of the autonomous vehicle based on geometric characteristic parameters;

[0040] Determine velocity constraints, acceleration constraints, and jerk constraints based on the kinematic model of the autonomous vehicle.

[0041] In an embodiment of the present application, determining the speed constraint, acceleration constraint, and jerk constraint based on the kinematic model of the autonomous driving vehicle includes:

[0042] Determine the linear velocity and angular velocity of each discrete path point in the pose sequence based on the kinematic model of the autonomous vehicle;

[0043] Determine velocity constraints based on the linear velocity and angular velocity of each discrete path point in the pose sequence;

[0044] Determine the acceleration of each discrete path point according to the linear velocity and angular velocity of each discrete path point in the pose sequence;

[0045] The acceleration constraint and the jerk constraint are determined based on the acceleration of each discrete path point.

[0046] In an embodiment of the present application, the method further includes:

[0047] Get the steering wheel angle of the autonomous vehicle;

[0048] The minimum turning radius constraint is determined based on the steering wheel angle and geometric characteristic parameters.

[0049] In an embodiment of the present application, determining an initial lane change path for the autonomous driving vehicle based on obstacle information and target lane position information includes:

[0050] Convert the target lane position information to the autonomous vehicle coordinate system to obtain the target position coordinates;

[0051] Get the current position coordinates of the autonomous vehicle;

[0052] Multiple intermediate points in the line connecting the current position coordinates and the target position coordinates are obtained through linear interpolation to obtain the initial lane change path.

[0053] A second aspect of the present application provides a device for controlling a vehicle lane change, comprising:

[0054] a memory configured to store instructions; and

[0055] The processor is configured to call instructions from the memory and implement the above-mentioned method for controlling the boom when executing the instructions.

[0056] A third aspect of the present application provides a machine-readable storage medium having stored thereon instructions for causing a machine to execute the above-mentioned method for controlling a vehicle lane change.

[0057] Through the above technical solution, after receiving the lane change signal, the obstacle information and target lane position information around the autonomous vehicle are collected; then the initial lane change path of the autonomous vehicle is determined based on the obstacle information and the target lane position information; the kinematic constraints of the autonomous vehicle are determined; and then the target optimization function is determined based on the initial lane change path and the kinematic constraints; then the target lane change path of the autonomous vehicle is determined through the target optimization function; finally, the corresponding control decision is generated based on the target lane change path to control the driving of the autonomous vehicle. This application can further generate the target lane change path of the autonomous vehicle through the kinematic constraints of the autonomous vehicle, taking into account the global nature of the planned path, which is conducive to planning a reasonable path more efficiently.

[0058] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present application but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0060] Figure 1 A flowchart of a method for controlling vehicle lane change provided in an embodiment of the present application;

[0061] Figure 2 A schematic diagram of the geometric configuration of an autonomous driving vehicle provided in a specific embodiment of the present application;

[0062] Figure 3 A schematic diagram of a kinematic model of an autonomous driving vehicle provided in a specific embodiment of the present application;

[0063] Figure 4 A structural block diagram of a device for controlling vehicle lane changing provided in an embodiment of the present application.

[0064] Among them, 410 is a memory; 420 is a processor. DETAILED DESCRIPTION

[0065] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0066] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly.

[0067] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0068] Figure 1 A flow chart of a method for controlling vehicle lane change provided in an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a method for controlling vehicle lane change, which is applied to an autonomous driving vehicle. The method may include the following steps:

[0069] Step 101: Receive a lane change signal;

[0070] Step 102: Obtain target lane position information;

[0071] Step 103: Determine an initial lane change path for the autonomous driving vehicle based on the target lane position information;

[0072] Step 104: Determine the kinematic constraints of the autonomous driving vehicle;

[0073] Step 105: Determine a target optimization function based on the initial lane change path and kinematic constraints;

[0074] Step 106: Determine a target lane change path for the autonomous driving vehicle using a target optimization function;

[0075] Step 107: Generate a corresponding control decision based on the target lane change path to control the driving of the autonomous driving vehicle.

[0076] In embodiments of the present application, an autonomous vehicle may be equipped with an automatic lane change system, which may be composed of a human-machine interaction system, an environmental perception system, and a lane change trajectory planning system. The automatic lane change system, combined with the method for controlling vehicle lane changes provided in embodiments of the present application, can automatically control lane changes for the autonomous vehicle.

[0077] Specifically, a lane change signal is first received. The lane change signal can be sent by the driver through the human-computer interaction system. When the driver sends the lane change signal, the autonomous vehicle begins to attempt the lane change operation. The target lane position information is the target position that the autonomous vehicle needs to reach after changing lanes. In one example, the processor can obtain environmental information around the vehicle through the environmental perception system, detect obstacles around the vehicle, and search for the target lane, thereby obtaining the target lane position information. The environmental perception system may include devices such as radar and cameras. After obtaining the target lane position information, the initial lane change path of the autonomous vehicle can be determined based on the target lane position information; the initial lane change path is the lane change path of the autonomous vehicle before optimization. In one example, the target lane position information can be converted to the autonomous vehicle coordinate system to obtain the target position coordinates, and then the initial lane change path is determined based on the target position coordinates and the current position coordinates of the autonomous vehicle.

[0078] In an embodiment of the present application, to optimize the initial lane change path of an autonomous vehicle, a modified TEB (Timed Elastic Band) algorithm can be used to optimize and solve the initial lane change path to obtain a target lane change path. In one example, a series of discrete poses with time information can be obtained from the initial lane change path. These discrete poses can then be combined into a trajectory that meets the goals of minimizing time, minimizing distance, and avoiding obstacles through graph optimization, while also satisfying the kinematic constraints of the autonomous vehicle.

[0079] In an embodiment of the present application, a lane change trajectory planning system can be used to plan a target lane change path that satisfies the kinematic characteristics of an autonomous vehicle based on an initial lane change path. The target lane change trajectory is the optimal path for the autonomous vehicle to change lanes from its current position to its target position. Specifically, corresponding constraints, namely the kinematic constraints of the autonomous vehicle, are first established based on the vehicle model of the autonomous vehicle. A TEB trajectory model is then constructed based on the initial lane change path. In one example, the kinematic constraints of the autonomous vehicle may include a speed constraint, an acceleration constraint, a jerk constraint, a minimum turning radius constraint, a lane boundary distance constraint, and a minimum time constraint. Jerk, also known as jerk or force rate, is the rate of change of acceleration. Furthermore, the aforementioned constraints are applied to the TEB trajectory model to determine a target optimization function. This target optimization function is the function that solves the target lane change trajectory after incorporating the kinematic constraints of the autonomous vehicle. Optimizing and solving the target optimization function yields the target lane change trajectory of the autonomous vehicle. Finally, corresponding control decisions can be generated based on the target lane change path to control the autonomous vehicle's movement. In one example, the generated target lane change trajectory can be sent to the vehicle control system through the lane change trajectory planning system. The vehicle control system can convert the received target lane change path into corresponding control parameters, such as throttle, brake, and steering wheel angle control signals, to control the autonomous driving vehicle to drive to the target position along the target lane change path.

[0080] Through the above technical solution, after receiving the lane change signal, the obstacle information and target lane position information around the autonomous vehicle are collected; then the initial lane change path of the autonomous vehicle is determined based on the obstacle information and the target lane position information; the kinematic constraints of the autonomous vehicle are determined; and then the target optimization function is determined based on the initial lane change path and the kinematic constraints; then the target lane change path of the autonomous vehicle is determined through the target optimization function; finally, the corresponding control decision is generated based on the target lane change path to control the driving of the autonomous vehicle. This application can further generate the target lane change path of the autonomous vehicle through the kinematic constraints of the autonomous vehicle, taking into account the global nature of the planned path, which is conducive to planning a reasonable path more efficiently.

[0081] In this embodiment of the present application, step 103, determining the initial lane change path of the autonomous driving vehicle based on the target lane position information, may include:

[0082] Convert the target lane position information to the autonomous vehicle coordinate system to obtain the target position coordinates;

[0083] Get the current position coordinates of the autonomous vehicle;

[0084] Multiple intermediate points in the line connecting the current position coordinates and the target position coordinates are obtained through linear interpolation to obtain the initial lane change path.

[0085] In the embodiments of the present application, the target position coordinates are the coordinates of the position reached by the autonomous vehicle after changing lanes. To facilitate calculations, a coordinate system can be established based on the autonomous vehicle, and all parameters can be converted to the autonomous vehicle coordinate system to facilitate subsequent calculations and control of the autonomous vehicle. After collecting obstacle information around the autonomous vehicle and obtaining target lane position information, the processor can convert the target lane position information to the autonomous vehicle coordinate system through coordinate transformation to obtain the target position coordinates. Furthermore, the processor can also obtain the current position coordinates of the autonomous vehicle and then use linear interpolation to obtain multiple points on the line connecting the current position coordinates and the target position coordinates to obtain the initial lane change path for the autonomous vehicle from the current position to the target position. In this way, establishing a coordinate system based on the autonomous vehicle and combining the coordinates of the autonomous vehicle's current position and target position to determine the initial lane change path provides a basis for subsequent calculations, making it faster to solve the target lane change path.

[0086] Specifically, the processor can connect the current position coordinates and the target position coordinates of the autonomous vehicle, and then use linear interpolation in the horizontal and vertical directions to obtain the intermediate point to form the initial lane change path. In one example, the horizontal coordinate x direction of the intermediate point obtained by linear interpolation can satisfy formula (1) and formula (2):

[0087]

[0088] p ix =cof x *i; (2)

[0089] Similarly, the y-axis can satisfy formulas (3) and (4):

[0090]

[0091] p iy =cof y *i;(4)

[0092] Among them, cof x is the average lateral distance deviation between two adjacent points, dis x is the lateral distance deviation between the current position and the target position, cof y is the longitudinal distance deviation between two adjacent points, dis y is the longitudinal distance deviation between the current position and the target position, num is the number of inserted points, i represents the i-th point, the value range of i is [0, num], the middle point i is [p ix,p iy ], p ix is the horizontal coordinate of the middle point i, p iy is the ordinate of the middle point i.

[0093] In an embodiment of the present application, step 104, determining the kinematic constraints of the autonomous driving vehicle, may include:

[0094] Obtaining geometric characteristic parameters of the autonomous driving vehicle;

[0095] Construct a kinematic model of the autonomous vehicle based on geometric characteristic parameters;

[0096] Determine velocity constraints, acceleration constraints, and jerk constraints based on the kinematic model of the autonomous vehicle.

[0097] In the embodiment of the present application, the geometric characteristic parameters of the autonomous driving vehicle may include data such as the axle length and vehicle width of the autonomous driving vehicle. A kinematic model of the vehicle can be established based on the geometric characteristics of the autonomous driving vehicle. Figure 2 This is a schematic diagram of the geometric configuration of an autonomous driving vehicle provided in a specific embodiment of the present application. Figure 2 As shown, the kinematic model of the autonomous driving vehicle can satisfy formula (5):

[0098]

[0099] in, is the derivative of the posture state of the autonomous vehicle, is the speed in the x-axis direction, is the velocity in the y-axis direction, is the angular velocity, v(t) is the velocity of the autonomous vehicle at time t, β(t) is the turning angle of the autonomous vehicle at time t, L is the axis length of the autonomous vehicle, φ(t) is the virtual turning angle of the autonomous vehicle at time t, and φ(t) has a range of values ​​due to the steering geometry of the autonomous vehicle.

[0100] Furthermore, based on the autonomous vehicle's kinematic model and combined with its own performance, the vehicle's speed constraints, acceleration constraints, and jerk constraints can be determined. This provides constraints for optimizing the vehicle's lane change path.

[0101] In the embodiment of the present application, step 105, determining the target optimization function based on the initial lane change path and the kinematic constraints, may include:

[0102] The initial lane change path is converted into multiple discrete path points with pose information to obtain the pose sequence corresponding to the initial lane change path;

[0103] Determine the time series corresponding to the pose sequence;

[0104] Merge the pose sequence and time series to obtain the function to be optimized;

[0105] The target optimization function is determined based on the function to be optimized and the kinematic constraints.

[0106] In the embodiment of the present application, since the initial lane change path is only the line connecting the current position and the target position of the autonomous vehicle, the constraints of the vehicle's own motion dynamics and the constraints of the surrounding environment have not been considered. In order to convert the initial lane change path into a target lane change path that meets the autonomous vehicle's own kinematic constraints and avoids surrounding obstacles, the initial path can be discretized into multiple points, and then each point is processed and solved to determine the position information of each point. At the same time, considering the driving time constraint of the autonomous vehicle, the time information corresponding to each point can be determined, and the time information is combined with the position information and optimized to finally determine the target lane change path. After determining the initial lane change path of the autonomous vehicle, in order to determine the target lane change path based on the initial lane change path, the initial lane change path needs to be optimized. In one example, the global path can be modified by constructing a TEB trajectory model, and then the target optimization function is determined in combination with the kinematic constraints of the autonomous vehicle, and then the target optimization function is solved to obtain the target lane change path.

[0107] Specifically, the initial lane change path can be constructed as discrete path points with posture information, and the posture state is defined as S i =(x i ,y i ,β i ) T , then the vehicle's posture sequence in the world coordinate system can satisfy formula (6):

[0108] Q={S i}, i=0, 1,...,n; (6)

[0109] Among them, S i is the posture state of point i, x i and y i is the position information of the vehicle at point i, x i is the horizontal coordinate of the vehicle at point i, y i is the vertical coordinate of the vehicle at point i, β i is the turning angle of the vehicle at point i, that is, the direction angle, Q is the posture sequence, and n is the number of posture points.

[0110] The pose S of the trajectory model described by TEB i to S i+1 The time interval is ΔT i , then the time interval sequence corresponding to n postures can satisfy formula (7):

[0111] Δτ={ΔT i}, i=0, 1,..., n-1; (7)

[0112] Among them, Δτ is the time interval sequence corresponding to the pose sequence, ΔT i is the posture S i to S i+1 time interval.

[0113] Each time interval represents the time it takes for the autonomous vehicle to move from one pose to another. The TEB trajectory model contains pose sequence information and time interval sequence information. The trajectory information, i.e., the function to be optimized, can satisfy formula (8):

[0114] B=(Q, Δτ); (8)

[0115] Among them, B is the trajectory information of the initial path, and Q is the pose sequence.

[0116] Finally, the target optimization function is determined based on the function to be optimized and the kinematic constraints of the autonomous vehicle. This target optimization function is then solved to obtain the target lane change path. This improved TEB algorithm modifies the global path, taking into account the global nature of path planning and enabling more efficient and reasonable path planning.

[0117] In an embodiment of the present application, the kinematic constraints of the autonomous driving vehicle may include:

[0118] Speed ​​constraints, acceleration constraints, jerk constraints, minimum turning radius constraints, lane boundary distance constraints, and minimum time constraints.

[0119] In an embodiment of the present application, kinematic constraints of the autonomous vehicle are introduced to optimize the initial lane change path of the autonomous vehicle. Corresponding constraints can be established based on the vehicle model of the autonomous vehicle to modify the initial lane change path and determine the target lane change path. The constraints, i.e., the kinematic constraints of the autonomous vehicle, can include speed constraints, acceleration constraints, jerk constraints, minimum turning radius constraints, lane boundary constraints, and minimum time constraints. The speed constraint is a speed constraint that the autonomous vehicle's speed must meet; the acceleration constraint is an acceleration constraint that the autonomous vehicle's acceleration must meet; the jerk constraint is a jerk constraint that the autonomous vehicle's jerk must meet; the minimum turning radius constraint is a turning radius constraint that the autonomous vehicle must meet; the lane boundary constraint is a distance constraint that the autonomous vehicle must meet from the lane boundary; and the minimum time constraint is a constraint imposed to ensure that the autonomous vehicle reaches the target location as quickly as possible by minimizing the square of the sum of all time intervals.

[0120] By further optimizing path planning using the above constraints, the planned target lane change path can meet the kinematic characteristics of the autonomous vehicle. Furthermore, in addition to speed constraints, acceleration constraints, and minimum time constraints, jerk constraints, minimum turning radius constraints, and lane boundary distance constraints are added, making vehicle driving smoother and acceleration smoother, thereby improving the user's riding experience.

[0121] In an embodiment of the present application, determining the speed constraint, acceleration constraint, and jerk constraint based on the kinematic model of the autonomous driving vehicle may include:

[0122] Determine the linear velocity and angular velocity of each discrete path point in the pose sequence based on the kinematic model of the autonomous vehicle;

[0123] Determine velocity constraints based on the linear velocity and angular velocity of each discrete path point in the pose sequence;

[0124] Determine the acceleration of each discrete path point according to the linear velocity and angular velocity of each discrete path point in the pose sequence;

[0125] The acceleration constraint and the jerk constraint are determined based on the acceleration of each discrete path point.

[0126] Figure 3 This is a schematic diagram of the kinematic model of an autonomous driving vehicle provided in a specific embodiment of the present application. Figure 3 As shown, in the embodiment of the present application, the linear velocity and angular velocity of each discrete path point in the posture sequence can be determined based on the kinematic model of the autonomous driving vehicle. Figure 3It can be obtained that the linear velocity of each discrete path point can satisfy formula (9):

[0127]

[0128] Among them, Δβ k <<1.

[0129] The angular velocity of each discrete path point can satisfy formula (10):

[0130]

[0131] Among them, v k is the linear velocity of the autonomous vehicle at point k, ω k is the angular velocity of the autonomous vehicle at point k, ρ k is the turning radius of the autonomous vehicle at point k, γ is the function expression, Δβ k is the difference between the turning angle of the autonomous vehicle at point k+1 and the turning angle at point k, ΔT k is the time interval between the autonomous vehicle at point k and point k+1, s k is the position information of the autonomous driving vehicle at point k, d k is the distance between point k and point k+1 of the autonomous driving vehicle, due to Δβ k <<1,d k Approximate arc length.

[0132] In the embodiment of the present application, the speed constraint can be determined according to the linear velocity and angular velocity of each discrete path point in the pose sequence, and the speed constraint can satisfy formula (11):

[0133]

[0134] in, is the acceleration constraint, s k is the position information of the autonomous driving vehicle at point k, v max The maximum linear speed of the autonomous vehicle, v k is the linear velocity of the autonomous vehicle at point k, ω max is the maximum acceleration of the autonomous vehicle, ω k is the angular velocity of the autonomous vehicle at point k, ΔT k The time interval between the autonomous vehicle at point k and point k+1, T is the running time of the autonomous vehicle;

[0135] In the embodiment of the present application, the acceleration of the middle point can be obtained based on the linear velocities of the three adjacent points in the posture sequence. The acceleration of the middle point satisfies formula (12):

[0136]

[0137] Among them, v k+1 is the linear velocity of the autonomous vehicle at point k+1, ΔT k+1 The time difference between the autonomous driving vehicle at point k+1 and point k+2.

[0138] The acceleration of each discrete path point can be determined according to the linear velocity of each discrete path point in the pose sequence, and then the acceleration constraint can be determined according to the acceleration of each discrete path point. The acceleration constraint can satisfy formula (13):

[0139] a k (s k+2 ,s k+1 ,s k ,ΔT k+1 ,ΔT k )=a max -|a k |; (13)

[0140] Among them, a k is the acceleration constraint, a max is the maximum acceleration of the autonomous vehicle, a k is the acceleration of the autonomous vehicle at point k;

[0141] In the embodiment of the present application, in order to ensure smoothness during acceleration of the autonomous vehicle, a jerk constraint can be introduced. The jerk of each discrete path point can be determined based on the acceleration of each discrete path point in the pose sequence. The jerk of each discrete path point can then satisfy formula (14):

[0142]

[0143] Among them, j k is the acceleration of the autonomous vehicle at point k, a k+1 is the acceleration of the autonomous vehicle at point k+1.

[0144] Furthermore, the jerk constraint of the autonomous driving vehicle can be determined based on the jerk of each discrete point in the pose sequence, and the jerk constraint can satisfy formula (15):

[0145]

[0146] in, is the jerk constraint, j max is the maximum acceleration of the autonomous vehicle, j k is the acceleration of the autonomous vehicle at point k.

[0147] In an embodiment of the present application, the method may further include:

[0148] Get the steering wheel angle of the autonomous vehicle;

[0149] The minimum turning radius constraint is determined based on the steering wheel angle and geometric characteristic parameters.

[0150] In the embodiment of the present application, the minimum turning radius constraint of the vehicle can be determined based on the steering wheel angle and geometric characteristic parameters of the autonomous driving vehicle. Figure 2 It can be seen that the turning radius of the autonomous driving vehicle satisfies formula (16):

[0151]

[0152] Among them, Δβ k <<1,ρ k is the turning radius of the autonomous vehicle.

[0153] Furthermore, the minimum turning radius of the autonomous vehicle can satisfy formula (17):

[0154] ρ k ≥ρ min ; (17)

[0155] Among them, ρ min is the minimum turning radius of the autonomous vehicle.

[0156] In an embodiment of the present application, determining the kinematic constraints of the autonomous driving vehicle may further include:

[0157] Collect obstacle information around the autonomous vehicle;

[0158] The lane boundary constraints are determined based on the pose sequence and obstacle information corresponding to the initial lane change path.

[0159] In the embodiment of the present application, the minimum distance constraint between the autonomous driving vehicle and the lane boundary, i.e., the lane boundary constraint, can be determined based on the acquired obstacle information around the autonomous driving vehicle. In one example, δ(s k ,Ο) is the pose point s k The minimum distance to the lane boundary O, then the lane boundary constraint can satisfy formula (18):

[0160] o k (s k )=[δ(s k ,Ο1),δ(s k ,Ο2),···,δ(s k ,Ο R )] T -[δ min ,δ min ,···,δ min ]T ; (18)

[0161] Where R is the number of lane boundaries, o k is the lane boundary constraint, and T is the running time of the autonomous vehicle.

[0162] In the embodiment of the present application, the shortest time constraint may satisfy formula (19):

[0163] f(k)=ΔT k 2 ; (19)

[0164] Among them, f(k) is the functional expression of the shortest time constraint, ΔT k 2 The shortest time constraint.

[0165] In the embodiment of the present application, based on the aforementioned multiple constraints, a target optimization function is determined from the perspective of time and posture state, the initial path is optimized in real time according to different weights, and the optimal path point is obtained through weighted multi-objective optimization, thereby obtaining the target lane change path of the autonomous driving vehicle. The target optimization function can satisfy formulas (20) and (21):

[0166]

[0167]

[0168] in, is the target lane change path, is the target optimization function, is the speed constraint, a k is the acceleration constraint, is the jerk constraint, ρ k is the minimum turning radius constraint, o k is the lane boundary distance constraint, ΔT k 2 is the shortest time constraint, and a, b, c, d, e and f are weighting coefficients.

[0169] In one example, after obtaining the target optimization function, the graph optimization tool G2O can be used to optimize and solve the target optimization function, ultimately obtaining the optimized trajectory, which is the target lane change trajectory of the autonomous vehicle. Finally, the vehicle control system converts the target lane change trajectory into control parameters for the autonomous vehicle, such as throttle, brake, and steering wheel angle control signals, to control the autonomous vehicle's movement along the target optimized path to the target position after the lane change.

[0170] Through the above technical solution, this application proposes a lane change trajectory planning method based on the improved TEB algorithm, analyzes the kinematic model of the autonomous driving vehicle, and analyzes the shortcomings of the existing lane change trajectory generation system. The improved TEB algorithm is used to optimize the initial lane change trajectory, and the original trajectory composed of a series of discrete path points is converted into a passable trajectory, so that the car can complete the lane change trajectory behavior. At the same time, the shortest distance constraint function is added, and the remaining target constraint functions are integrated, which can achieve the simultaneous consideration of the car's dynamic constraints and the fastest path. In addition, an acceleration constraint is introduced on the basis of the TEB algorithm to make the acceleration smoother. The introduction of the improved TEB algorithm not only improves the algorithm's operating efficiency, but also improves ride comfort.

[0171] Figure 4 This is a structural block diagram of a device for controlling vehicle lane change provided in an embodiment of the present application. Figure 4 As shown, an embodiment of the present application provides a device for controlling a vehicle lane change, which may include:

[0172] Memory 410 configured to store instructions; and

[0173] The processor 420 is configured to call instructions from the memory 410 and implement the above-mentioned method for controlling vehicle lane change when executing the instructions.

[0174] Specifically, in the embodiment of the present application, the processor 420 may be configured to:

[0175] receiving lane change signals;

[0176] Get the target lane position information;

[0177] Determine the initial lane change path of the autonomous vehicle based on the target lane position information;

[0178] Determine the kinematic constraints of an autonomous vehicle;

[0179] Determine the target optimization function based on the initial lane change path and kinematic constraints;

[0180] Determine the target lane change path of the autonomous driving vehicle through the target optimization function;

[0181] Generate corresponding control decisions based on the target lane change path to control the driving of the autonomous driving vehicle.

[0182] In this embodiment of the present application, the kinematic constraints of the autonomous driving vehicle include:

[0183] Speed ​​constraints, acceleration constraints, jerk constraints, minimum turning radius constraints, lane boundary distance constraints, and minimum time constraints.

[0184] In the embodiment of the present application, the target optimization function satisfies formula (20) and formula (21):

[0185]

[0186]

[0187] in, is the target lane change path, is the target optimization function, is the speed constraint, a k is the acceleration constraint, is the jerk constraint, ρ k is the minimum turning radius constraint, o k is the lane boundary distance constraint, ΔT k 2 is the shortest time constraint, and a, b, c, d, e and f are weighting coefficients.

[0188] In the embodiment of the present application, the speed constraint satisfies formula (11):

[0189]

[0190] in, is the acceleration constraint, s k is the position information of the autonomous driving vehicle at point k, v max The maximum speed of the autonomous vehicle, v k is the speed of the autonomous vehicle at point k, ω max is the maximum acceleration of the autonomous vehicle, ω k is the angular velocity of the autonomous vehicle at point k, ΔT k The time difference between the autonomous vehicle at point k and point k+1, T is the running time of the autonomous vehicle;

[0191] The acceleration constraint satisfies formula (13):

[0192] a k (s k+2 ,s k+1 ,s k ,ΔT k+1 ,ΔT k )=a max -|a k |; (13)

[0193] Among them, a k is the acceleration constraint, a max is the maximum acceleration of the autonomous vehicle, a k is the acceleration of the autonomous vehicle at point k, ΔT k+1The time difference between the autonomous vehicle at point k+1 and point k+2;

[0194] The jerk constraint satisfies formula (15):

[0195]

[0196] in, is the jerk constraint, j max is the maximum acceleration of the autonomous vehicle, j k is the acceleration of the autonomous vehicle at point k.

[0197] Furthermore, the processor 420 may be further configured to:

[0198] The initial lane change path is converted into multiple discrete path points with pose information to obtain the pose sequence corresponding to the initial lane change path;

[0199] Determine the time series corresponding to the pose sequence;

[0200] Merge the pose sequence and time series to obtain the function to be optimized;

[0201] The target optimization function is determined based on the function to be optimized and the kinematic constraints.

[0202] Furthermore, the processor 420 may be further configured to:

[0203] Collect obstacle information around the autonomous vehicle;

[0204] The lane boundary constraints are determined based on the pose sequence and obstacle information corresponding to the initial lane change path.

[0205] Furthermore, the processor 420 may be further configured to:

[0206] Obtaining geometric characteristic parameters of the autonomous driving vehicle;

[0207] Construct a kinematic model of the autonomous vehicle based on geometric characteristic parameters;

[0208] Determine velocity constraints, acceleration constraints, and jerk constraints based on the kinematic model of the autonomous vehicle.

[0209] Furthermore, the processor 420 may be further configured to:

[0210] Determine the linear velocity and angular velocity of each discrete path point in the pose sequence based on the kinematic model of the autonomous vehicle;

[0211] Determine velocity constraints based on the linear velocity and angular velocity of each discrete path point in the pose sequence;

[0212] Determine the acceleration of each discrete path point according to the linear velocity and angular velocity of each discrete path point in the pose sequence;

[0213] The acceleration constraint and the jerk constraint are determined based on the acceleration of each discrete path point.

[0214] Furthermore, the processor 420 may be further configured to:

[0215] Get the steering wheel angle of the autonomous vehicle;

[0216] The minimum turning radius constraint is determined based on the steering wheel angle and geometric characteristic parameters.

[0217] Furthermore, the processor 420 may be further configured to:

[0218] Convert the target lane position information to the autonomous vehicle coordinate system to obtain the target position coordinates;

[0219] Get the current position coordinates of the autonomous vehicle;

[0220] Multiple intermediate points in the line connecting the current position coordinates and the target position coordinates are obtained through linear interpolation to obtain the initial lane change path.

[0221] Through the above technical solution, after receiving the lane change signal, the obstacle information and target lane position information around the autonomous vehicle are collected; then the initial lane change path of the autonomous vehicle is determined based on the obstacle information and the target lane position information; the kinematic constraints of the autonomous vehicle are determined; and then the target optimization function is determined based on the initial lane change path and the kinematic constraints; then the target lane change path of the autonomous vehicle is determined through the target optimization function; finally, the corresponding control decision is generated based on the target lane change path to control the driving of the autonomous vehicle. This application can further generate the target lane change path of the autonomous vehicle through the kinematic constraints of the autonomous vehicle, taking into account the global nature of the planned path, which is conducive to planning a reasonable path more efficiently.

[0222] An embodiment of the present application also provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the above-mentioned method for controlling a vehicle to change lanes.

[0223] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0224] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0225] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0226] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0227] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0228] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0229] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0230] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0231] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for controlling a vehicle lane change, characterized in that: Applied to an autonomous driving vehicle, the method includes: receiving lane change signals; Get the target lane position information; determining an initial lane change path of the autonomous driving vehicle based on the target lane position information; Determining kinematic constraints of the autonomous vehicle, the kinematic constraints of the autonomous vehicle comprising a speed constraint, an acceleration constraint, a jerk constraint, a minimum turning radius constraint, a lane boundary distance constraint, and a minimum time constraint; determining a target optimization function based on the initial lane change path and the kinematic constraints; Determining a target lane change path of the autonomous driving vehicle using the target optimization function; Generating a corresponding control decision according to the target lane change path to control the driving of the autonomous driving vehicle; The objective optimization function satisfies formula (1) and formula (2): ；（1） ；（2） in, is the target lane change path, Optimize the function for the objective, is the speed constraint, is the acceleration constraint, is the jerk constraint, is the minimum turning radius constraint, is the lane boundary distance constraint, is the shortest time constraint, 、 、 、 、 and is the weighting coefficient.

2. The method according to claim 1, characterized in that The speed constraint satisfies formula (3): ；（3） in, is the acceleration constraint, For the autonomous driving vehicle The point pose information, the maximum speed of the autonomous vehicle, For the autonomous driving vehicle The speed of the point, is the maximum acceleration of the autonomous vehicle, For the autonomous driving vehicle The angular velocity of the point, The autonomous vehicle k Point and k+ 1 The time difference of points, The operating time of the autonomous vehicle; The acceleration constraint satisfies formula (4): ；（4） in, is the acceleration constraint, is the maximum acceleration of the autonomous vehicle, For the autonomous driving vehicle The acceleration of the point, For the autonomous driving vehicle k+1 Point and k+2 The time difference between points; The jerk constraint satisfies formula (5): ；（5） in, is the jerk constraint, is the maximum acceleration of the autonomous driving vehicle, For the autonomous driving vehicle The acceleration of the point.

3. The method according to claim 1, characterized in that Determining a target optimization function based on the initial lane change path and the kinematic constraints includes: Converting the initial lane change path into a plurality of discrete path points with posture information to obtain a posture sequence corresponding to the initial lane change path; Determining a time sequence corresponding to the posture sequence; Merging the pose sequence and the time sequence to obtain a function to be optimized; The target optimization function is determined according to the function to be optimized and the kinematic constraints.

4. The method according to claim 3, characterized in that Determining the kinematic constraints of the autonomous driving vehicle includes: Collecting obstacle information around the autonomous driving vehicle; The lane boundary distance constraint is determined according to a posture sequence corresponding to the initial lane change path and the obstacle information.

5. The method according to claim 3, characterized in that Determining the kinematic constraints of the autonomous driving vehicle includes: Obtaining geometric characteristic parameters of the autonomous driving vehicle; Constructing a kinematic model of the autonomous driving vehicle according to the geometric characteristic parameters; The velocity constraint, the acceleration constraint, and the jerk constraint are determined based on a kinematic model of the autonomous vehicle.

6. The method according to claim 5, characterized in that The determining the velocity constraint, the acceleration constraint, and the jerk constraint based on the kinematic model of the autonomous driving vehicle includes: Determining the linear velocity and angular velocity of each discrete path point in the pose sequence based on a kinematic model of the autonomous vehicle; Determining the velocity constraint based on the linear velocity and angular velocity of each discrete path point in the pose sequence; Determining the acceleration of each discrete path point in the pose sequence according to the linear velocity and angular velocity of each discrete path point; The acceleration constraint and the jerk constraint are determined according to the acceleration of each discrete path point.

7. The method according to claim 5, characterized in that The method further comprises: Obtaining a steering wheel angle of the autonomous driving vehicle; The minimum turning radius constraint is determined according to the steering wheel angle and the geometric characteristic parameter.

8. The method according to claim 1, characterized in that Determining an initial lane change path of the autonomous driving vehicle according to the target lane position information includes: Converting the target lane position information into the autonomous driving vehicle coordinate system to obtain the target position coordinates; Obtaining the current position coordinates of the autonomous driving vehicle; A plurality of intermediate points in a line connecting the current position coordinates and the target position coordinates are obtained by linear interpolation to obtain the initial lane change path.

9. A device for controlling a vehicle lane change, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instructions from the memory and implement the method for controlling vehicle lane change according to any one of claims 1 to 8 when executing the instructions.

10. A machine-readable storage medium, characterized in that The machine-readable storage medium stores instructions for causing a machine to execute the method for controlling lane change of a vehicle according to any one of claims 1 to 8.

Images