Method and apparatus for automated lane change based on lane centering holding

Abstract

The invention provides a method and device for realizing automatic lane change based on a lane centering keeping function. A method according to one aspect of the disclosure includes: determining a center line of a target lane as a lane changing target according to a current lane where a vehicle is located; whether the transverse distance between the vehicle and the center line of the target lane is smaller than a distance threshold value or not is judged; in response to determining that the lateral distance from the vehicle to the center line of the target lane is not less than the distance threshold, calculating a temporary target trajectory according to the center line of the target lane and the longitudinal speed of the vehicle, the temporary target trajectory being laterally deviated from the vehicle by a specified step length; and providing the temporary target trajectory as an input to a lane centering keeping function of the vehicle, in which the lane centering keeping function controls movement of the vehicle with the temporary target trajectory as a target center line.

Description

Technical Field

[0001] The present disclosure relates generally to advanced driver assistance systems (ADAS), and more particularly to methods and apparatus for implementing automatic lane change based on a lane centering function. Background Art

[0002] Advanced Driver Assistance System (ADAS) is a collection of software and hardware technologies used to assist drivers in driving. ADAS uses various sensors installed on the vehicle to collect environmental data around the vehicle and the vehicle's own operating data, and performs comprehensive calculations and analysis on these and other data to achieve various safety and adaptive functions, including early warning of dangerous conditions and erroneous driving behaviors, as well as vehicle control. ADAS can minimize human errors, improve road traffic safety, and enhance the driving experience.

[0003] Automatic lane change is a component of ADAS and is generally considered to be a L2+ ADAS function. This function is designed to control the vehicle to change lanes safely without driver intervention. The current mainstream automatic lane change functions are relatively complex to implement, which is not conducive to performance adjustment and rapid product iteration and update. Summary of the invention

[0004] In the summary section, some selected concepts are introduced in a simplified form, which will be further described in the detailed description section below. This summary section is not intended to identify any key features or essential features of the claimed subject matter, nor is it intended to be used to help determine the scope of the claimed subject matter.

[0005] According to one aspect of the present disclosure, a method for realizing automatic lane changing based on a lane centering keeping function is provided, the method comprising: determining the center line of a target lane as a lane changing target according to a current lane in which a vehicle is located; judging whether a lateral distance from the vehicle to the center line of the target lane is less than a distance threshold; in response to judging that the lateral distance from the vehicle to the center line of the target lane is not less than the distance threshold, calculating a temporary target trajectory line according to the center line of the target lane and the longitudinal speed of the vehicle, wherein the temporary target trajectory line deviates laterally from the vehicle by a specified step length; and providing the temporary target trajectory line as an input to the lane centering keeping function of the vehicle, wherein the lane centering keeping function controls the movement of the vehicle using the temporary target trajectory line as the target center line.

[0006] According to another aspect of the present disclosure, a device for realizing automatic lane change based on a lane centering function is provided, the device comprising: a module for determining the center line of a target lane as a lane change target according to a current lane in which a vehicle is located; a module for judging whether a lateral distance from the vehicle to the center line of the target lane is less than a distance threshold; a module for calculating a temporary target trajectory line according to the center line of the target lane and the longitudinal speed of the vehicle in response to judging that the lateral distance from the vehicle to the center line of the target lane is not less than the distance threshold, wherein the temporary target trajectory line deviates laterally from the vehicle by a specified step length; and a module for providing the temporary target trajectory line as an input to the lane centering function of the vehicle, wherein the lane centering function controls the movement of the vehicle with the temporary target trajectory line as the target center line.

[0007] According to another aspect of the present disclosure, a computing device is provided, comprising: at least one processor; and a memory coupled to the at least one processor and used to store instructions, wherein the instructions, when executed by the at least one processor, cause the at least one processor to perform the method described in the present disclosure.

[0008] According to yet another aspect of the present disclosure, a computer-readable storage medium is provided, on which instructions are stored. When the instructions are executed by at least one processor, the at least one processor executes the method described in the present disclosure.

[0009] According to another aspect of the present disclosure, a computer program product is provided, which includes instructions. When the instructions are executed by at least one processor, the at least one processor performs the method described in the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Implementations of the present disclosure are illustrated by way of example and not limitation in the accompanying drawings in which like reference numerals designate the same or similar parts and in which:

[0011] Figure 1 An exemplary vehicle driving scenario according to some implementations of the present disclosure is shown;

[0012] Figure 2 A flowchart illustrating an exemplary method according to some implementations of the present disclosure is shown;

[0013] Figure 3 A flowchart illustrating exemplary operations according to some implementations of the present disclosure is shown;

[0014] Figure 4 shows an example of heading angle error according to some implementations of the present disclosure;

[0015] Figure 5 A block diagram illustrating an exemplary apparatus according to some implementations of the present disclosure is shown;

[0016] Figure 6 A block diagram of an exemplary computing device according to some implementations of the present disclosure is shown.

[0017] List of reference numerals:

[0018] 100: Vehicle 110, 120: Lane 130, 140: Centerline of the lane

[0019] 150: Lane lines

[0020] 210: Determine the center line of the target lane based on the vehicle's current lane

[0021] 220: Determine whether the lateral distance from the vehicle to the center line of the target lane is less than the distance threshold

[0022] 230: Calculate the temporary target trajectory based on the center line of the target lane and the longitudinal speed of the vehicle

[0023] 240: Provides temporary target trajectory as input to the vehicle's lane centering function

[0024] 310: Determine the current lane of the vehicle

[0025] 320: Determine whether the current lane is the original lane used as the starting point for lane change

[0026] 330: Obtain the centerline of the target lane by shifting the centerline of the current lane by a specified amount related to the lane width

[0027] 340: Use the center line of the current lane as the center line of the target lane

[0028] 510-540: Module 610: Processor 620: Memory DETAILED DESCRIPTION

[0029] In the following description, a large number of specific details are set forth for the purpose of explanation. However, it should be understood that the implementation of the present disclosure can be implemented without these specific details. In other examples, well-known circuits, structures, and techniques are not shown in detail to avoid affecting the understanding of the description.

[0030] References throughout the specification to "an implementation," "implementation," "exemplary implementations," "some implementations," "various implementations," etc., indicate that the implementations of the present disclosure described may include specific features, structures, or characteristics, however, it does not mean that every implementation must include these specific features, structures, or characteristics. In addition, some implementations may have some, all, or none of the features described for other implementations.

[0031] In a manner that is most helpful for understanding the claimed subject matter, various operations may be described as multiple discrete actions or operations in sequence. However, the order of description should not be interpreted as implying that these operations are necessarily order-dependent. On the contrary, these operations may not be performed in the order presented. In other implementations, various other operations may also be performed, and / or various operations that have been described may be ignored.

[0032] In the specification and claims, the phrase "A and / or B" may appear to mean one of the following: (A), (B), (A and B). Similarly, the phrase "A, B and / or C" may appear to mean one of the following: (A), (B), (C), (A and B), (A and C), (B and C), (A and B and C).

[0033] In the specification and claims, the terms "coupled" and "connected" and their derivatives may be used. It should be understood that these terms are not intended as synonyms for each other. Instead, in a particular implementation, "connected" is used to indicate that two or more components are in direct physical or electrical contact with each other, while "coupled" is used to indicate that two or more components cooperate or interact with each other, but they may or may not be in direct physical or electrical contact.

[0034] As a component of the Advanced Driver Assistance System (ADAS), automatic lane change is one of the essential functions for achieving high-level driving automation. The current mainstream automatic lane change functions mainly use polynomial algorithms based on vehicle dynamic models to plan vehicle driving trajectories to achieve lane changes. However, this type of trajectory planning method is relatively complex to implement, which not only easily causes control problems such as steering wheel shaking and lane change overshoot, but also brings difficulties to performance adjustment, which is not conducive to the rapid iteration and update of products.

[0035] One purpose of the present disclosure is to provide a simple automatic lane change mechanism, which, as described in detail below, can achieve the automatic lane change function by making only a few adjustments based on the lane centering function (a basic L2 ADAS function). This function is particularly suitable for automatic lane change in less complex road environments, such as on highways and urban expressways. This implementation mechanism greatly reduces the complexity of the system and effectively overcomes many disadvantages in existing solutions.

[0036] First see Figure 1 , which shows an exemplary vehicle driving scenario according to some implementations of the present disclosure. It should be understood that for the purpose of clear illustration, Figure 1 Objects in the figure are not drawn to scale. Figure 1 1 shows two lanes, a lane 110 on the right and a lane 120 on the left adjacent thereto, the two lanes being separated by a lane line 150 therebetween. The vehicle 100 is currently traveling on the lane 110. In addition, for ease of description, Figure 1 Schematically showing a center line 130 of lane 110 and a center line 140 of lane 120 , it is to be understood that such center lines are usually not printed on the road surface in a real environment.

[0037] To achieve various types of driving assistance, a basic requirement is the ability to identify various objects in the vehicle's surroundings. Such objects may include, but are not limited to, roads (lane lines), vehicles, pedestrians, traffic lights, and the like. Lane line recognition is a prerequisite for monitoring and / or controlling the lateral (or sideways) movement of the vehicle. Taking vehicle 100 as an example, it at least has the ability to identify the left and / or right lane lines of the current lane 110. The identified lane lines are the basis for the correct operation of ADAS functions such as lane departure warning function and lane keeping function equipped on vehicle 110.

[0038] The vehicle 100 may be provided with various types of sensors for detecting the surrounding environment, including visual sensors, millimeter wave radars, ultrasonic radars, laser radars (LiDAR), etc., which can continuously detect objects appearing around the vehicle 100. As for lane line recognition, the following description is made with respect to lane line recognition based on visual sensors, but it is understandable that lane line recognition based on other technologies such as laser radar is also feasible, and the present disclosure is not limited thereto.

[0039] According to some implementations of the present disclosure, a visual sensor (not shown) equipped with vehicle 100 can capture road images during vehicle driving and provide them to an information processing unit (not shown) of vehicle 100. The information processing unit can identify lane lines around vehicle 100, such as the left and / or right lane lines of lane 110, by analyzing and processing the captured images.

[0040] In some implementations, the road image can be subjected to a series of image processing operations by the information processing unit of the vehicle 100, such as grayscale processing, filtering processing, binarization processing, etc., so as to better present the shape and contour of the lane line. Then, the lane line can be extracted by applying the selected lane line recognition method. Furthermore, by, for example, using the least squares method to perform curve fitting on the lane line data, typically a cubic curve, a curve equation representing the trajectory of the corresponding lane line can be obtained. The monitoring and / or control of the lateral movement of the vehicle in ADAS, such as the aforementioned lane departure warning function, lane keeping function, etc., can all be calculated based on such a curve equation.

[0041] Still Figure 1 For example, according to some implementations of the present disclosure, the cubic curves representing the left and / or right lane lines of the lane 110 may be determined in the above manner, and the cubic curve representing the center line 130 of the lane 110 may be determined accordingly. For example, the cubic curve representing the center line 130 of the lane 110 may be determined by averaging the two cubic curves representing the left lane line and the right lane line of the lane 110. However, other methods may also be used, such as averaging the two cubic curves representing the left lane line and the right lane line of the lane 110 to determine the cubic curve representing the center line 130 of the lane 110. Figure 1 The third curve of the left lane line 150 of the lane 110 shown in FIG. 1 is used to determine the third curve of the center line 130 of the corresponding lane, but the present disclosure is not limited thereto. For the vehicle 100 currently traveling in the lane 110, the center line 130 of the lane 110 is the target center line of the lane centering function of the vehicle. In other words, the goal of the lane centering function of the vehicle 100 is to make the vehicle 100 stably travel along the trajectory of the center line 130 through calculation and control.

[0042] Similar to the lane line, the cubic curve representing the center line 130 of the lane 110 can be expressed as follows:

[0043]

[0044] Among them, c0, c1, are the constant term, linear term coefficient, quadratic term coefficient, and cubic term coefficient of the curve equation. Here, c0, c1, c2, and c3 represent the lateral deviation, heading angle, curvature, and curvature change rate of this trajectory line, respectively.

[0045] According to some implementations of the present disclosure, a mechanism for implementing automatic lane change based on a lane centering function is provided. Figure 1An exemplary but non-limiting scenario is given for illustration, where a vehicle 100 is currently traveling in a lane 110, and a lane change requirement / instruction appears, more specifically, a lane change to the left. For the application scenario of a vehicle changing lanes, the current lane 110 is the original lane as the starting point of the lane change; and the lane 120 immediately adjacent to the left side of the current lane 110 is the target lane as the target of the lane change.

[0046] Reference below Figure 2 , a flowchart of an exemplary method 200 according to some implementations of the present disclosure is shown. The method 200 may be, for example, Figure 1 The one or more information processing units and / or control units in the vehicle 100 shown in the figure are executed to implement the mechanism described herein for implementing automatic lane change based on the lane centering function.

[0047] As shown, the exemplary method 200 begins at step 210. In this step, according to the current lane in which the vehicle is located (e.g., Figure 1 110) to determine the center line of the target lane as the lane change target (eg, Figure 1 140 of lane 120 shown in FIG. 1 ).

[0048] After determining the center line of the target lane at step 210 , method 200 may proceed to step 220 , where it is determined whether the lateral distance from the vehicle to the center line of the target lane is less than a distance threshold.

[0049] In response to the judgment result of step 220 being "No", that is, the lateral distance from the vehicle to the center line of the target lane is not less than the distance threshold, method 200 proceeds to step 230, and a temporary target trajectory line is calculated based on the center line of the target lane and the longitudinal speed of the vehicle, wherein the temporary target trajectory line deviates from the lateral direction of the vehicle by a specified step length.

[0050] After calculating the temporary target trajectory in step 230, method 200 proceeds to step 240, in which the calculated temporary target trajectory is provided as input to a lane centering function, wherein the lane centering function controls vehicle motion using the temporary target trajectory as a target centerline.

[0051] According to some implementations of the present disclosure, the steps of method 200 are iteratively executed until it is determined that the lateral distance from the vehicle to the center line of the target lane is less than the distance threshold. That is, after each execution of step 240, the method flow will jump back to step 210 to start the next round of execution, and so on, until in a certain round of execution, it is found in step 220 that the lateral distance from the vehicle to the center line of the target lane is less than the distance threshold (that is, the judgment result of this step is "yes"), thereby terminating the execution of method 200.

[0052] According to some implementations of the present disclosure, the jump from step 240 to step 210 may be triggered by a timer. For example, a round of the process of method 200 may be executed in each sampling period applicable to the lane centering function. However, other implementation mechanisms are also possible.

[0053] Continue to view Figure 1 As mentioned above, for the vehicle 100 currently traveling in the lane 110, the center line 130 of the current lane 110 is always the target center line of the lane centering function of the vehicle. According to the automatic lane changing mechanism proposed in the present disclosure, in each round of control process, a calculated temporary target trajectory line is used to replace the center line of the current lane, and is provided as an input to the lane centering function to serve as the target center line, and the lane centering function is used to control the vehicle movement (including lateral movement). The calculation of the temporary target trajectory line not only takes into account the center line 150 of the determined target lane 120, but also takes into account the longitudinal speed of the vehicle 100. The calculated temporary target trajectory line deviates laterally from the vehicle 100 by a specified step length. According to some implementations of the present disclosure, the specified step length can be a fixed value, such as 0.2 meters, throughout the automatic lane changing process, but the present disclosure is not limited to this. That is to say, in each round of control, when executing step 230, a temporary target trajectory line will be calculated, which is laterally spaced from the vehicle 100 by the specified step length and is closer to the center line 150 of the target lane 120. The lane centering keeping function that receives the temporary target trajectory line will control the vehicle based on this target.

[0054] The following will refer to Figure 1 The following is an exemplary scenario to continue discussing some implementations and examples of the various steps of method 200.

[0055] According to some implementations of the present disclosure, the exemplary method 200 may be initiated based on detecting / receiving a lane change instruction. In some implementations, the driver of the vehicle 100 may manually turn on the turn signal of the vehicle 100 to explicitly issue a lane change instruction to the vehicle 100. Figure 1 In the illustrated scenario, the vehicle 100 is currently traveling on the lane 110 . The driver turns on the left turn signal at this moment, and the vehicle 100 receives an instruction to change lanes to the left, that is, the vehicle 100 is to change lanes to the left to the lane 120 .

[0056] In other implementations, the lane change command may also be automatically generated by the vehicle 100 according to the current surrounding environment and the vehicle driving state. For example, the vehicle 100 may be operating under certain high-level automatic driving conditions. At this moment, the vehicle 100 detects that there is an obstacle in front of the current lane 110, the front vehicle is moving slowly, and detects that the surrounding lanes (here, the left lane 120) are currently vacant and safe, so it automatically issues a left lane change command. It is understandable that other mechanisms for triggering the method 200 to start are also feasible, and the present disclosure is not limited thereto.

[0057] Go to Figure 3 , which shows a flow chart of an exemplary operation 300 according to some implementations of the present disclosure. More specifically, the illustrated operation 300 may correspond to an exemplary implementation of step 210 of the aforementioned method 200.

[0058] Step 210 is to determine the center line of the target lane as the lane change target according to the current lane where the vehicle is located. Figure 3 As shown, exemplary operations 300 may include step 310 , in which a current lane in which a vehicle is located is determined.

[0059] According to some implementations of the present disclosure, the information processing unit of vehicle 100 can receive road images captured by the visual sensor of vehicle 100, and determine the lane 110 (including its left and / or right lane lines) in which vehicle 100 is currently located based on analysis, processing and calculation of the road images.

[0060] After determining the current lane in which the vehicle is located, the exemplary operation 300 may proceed to step 320 to determine whether the current lane is the original lane serving as the starting point of the lane change.

[0061] exist Figure 1 In the example shown, the vehicle 100 is changing lanes from the lane 110 it is currently in to the lane 120 to the left, so the current lane 110 is the original lane as the starting point of the lane change, and the lane 120 immediately adjacent to the left is the target lane as the target of the lane change. In this case, the judgment result of step 320 is "yes".

[0062] In response to a “yes” answer at step 320 , exemplary operation 300 may proceed to step 330 , where the centerline of the target lane is obtained by laterally shifting the centerline of the current lane by a specified amount related to the lane width.

[0063] In some implementations of the present disclosure, as described above, the information processing unit of the vehicle 100 can determine a cubic curve representing the center line 130 of the current lane 110 based on the determined cubic curves representing the left and / or right lane lines of the current lane 110, and the coefficients c0, c1, c2, and c3 in the curve equation respectively represent the lateral deviation, heading angle, curvature, and curvature change rate of the trajectory line. Therefore, in step 330, the corresponding cubic curve representing the center line 140 of the target lane 120 can be obtained by lateral shifting the cubic curve by a specified size related to the lane width.

[0064] Therefore, according to some implementations of the present disclosure, the heading angle c of the centerline 140 of the target lane 120 is 1_tc , curvature c 2_tc and the curvature change rate c 3_tc The heading angle c1, curvature c2 and curvature change rate c3 of the center line 130 of the current lane 110 are the same; the difference between the two is that the lateral deviation c 0_tc The lateral deviation c0 from the center line 130 of the current lane 110 differs by a specified size related to the lane width. In some implementations, the specified size may correspond to the sum of half the lane width of the current lane 110 and half the lane width of the target lane 120. In other implementations, for the purpose of simplicity and / or for a less complex road environment, assuming that the lane width of the current lane 110, or a general value of the lane width, is 3.5 meters, then the specified size may also be set to approximately 3.5 meters, i.e., a value equal to or close to the lane width of the current lane 110 or a general lane width. If the positive direction in the lateral direction is represented by left (however, the present disclosure is not limited thereto), for Figure 1 In the example shown, c 0_tc Larger than c0 by the specified size (e.g., 3.5 meters).

[0065] A simple mechanism for determining the centerline 140 of the target lane 120 based on the centerline 130 of the current lane 110 is provided herein. However, it should be understood that other methods for determining the centerline of the target lane are also feasible and the present disclosure is not limited to a specific method.

[0066] Back to Figure 2 Next, let's look at step 220 in method 200, determining whether the lateral distance from the vehicle to the center line of the target lane is less than a distance threshold. According to some implementations of the present disclosure, the distance threshold may be related to the vehicle control capability of the lane centering function equipped by the vehicle 100. As an example, the distance threshold may be 0.3 meters; however, other values ​​are also possible, and the present disclosure is not limited thereto.

[0067] continue Figure 1 In the example of FIG. 1 , at the beginning of the lane change (for example, just after the aforementioned control process is initiated in response to the lane change instruction), the vehicle 100 is still traveling in the current lane / original lane 110 and away from the center line 140 of the target lane 120. Figure 1 As shown, the vehicle 100 may even be at the right side of the center line 130 of the current lane 110 at this moment, so the lateral distance between the vehicle 100 and the center line 140 of the target lane 120 exceeds the width of one lane (for example, 3.5 meters). Accordingly, the judgment result of step 220 at this moment is "no", that is, the lateral distance from the vehicle 100 to the center line 140 of the target lane 120 is not less than the distance threshold (0.3 meters).

[0068] According to the current determination result of step 220 , method 200 decides to proceed to step 230 to calculate a temporary target trajectory according to the center line of the target lane and the longitudinal speed of the vehicle.

[0069] According to some implementations of the present disclosure, the temporary target trajectory line deviates laterally from the vehicle 100 by a specified step size (eg, 0.2 m), which is reflected in the lateral deviation of the temporary target trajectory line, i.e., the constant term c of the cubic curve. 0_temp superior.

[0070] According to some implementations of the present disclosure, the selection of the designated step length is based on the consideration of vehicle control smoothness, and the lateral error caused is reduced by setting a suitable small step length to ensure the smoothness of lane change. In some implementations, the designated step length may be a fixed value selected from a certain range, and the range may be related to the calibration of the vehicle. In some examples, the range may be 0.15 meters to 0.2 meters. In some implementations, the designated step length is not always a fixed value throughout the automatic lane change process, but may be variable depending on the lateral distance from the vehicle 100 to the center line 140 of the target lane 120, and this change in step length may still be within a certain range. In some examples, in the early stage of the lane change process, the step length can be set to a slightly smaller value (e.g., 0.15 meters), for example, to avoid excessive steering movements; in the middle stage of the lane change process, the step length can be set to a slightly larger value (e.g., 0.2 meters), for example, to allow the vehicle 100 to quickly cross the middle lane line 150; and in the later stage of the lane change, as the vehicle 100 becomes closer to the center line 140 of the target lane 120, the step length can be set to a slightly smaller value (e.g., 0.15 meters, which may also be different from the step length value set for the initial stage), for example, to reduce steering wheel movements. Other settings for the step length change during the lane change process are also possible. According to some implementations of the present disclosure, the specific value of the step length can be obtained by looking up a table using the lateral distance from the vehicle 100 to the center line 140 of the target lane 120. The table can also be determined based on the calibration of the vehicle.

[0071] According to some implementations of the present disclosure, the calculation of the temporary target trajectory may be performed in the following manner.

[0072] In some implementations, the lateral deviation c of the temporary target trajectory 0_temp can be calculated as:

[0073] c 0_temp =signum(c 0_tc )×p Step

[0074] Among them, c 0_tc represents the lateral deviation of the center line of the target lane, p Step Represents the specified step size, signum() is the sign function.

[0075] In some implementations, the heading angle c of the temporary target trajectory is 1_temp can be calculated as:

[0076]

[0077] Among them, c 1_tcrepresents the heading angle of the center line of the target lane, v represents the longitudinal speed of the vehicle, and p Time Represents the time parameter.

[0078] In addition, in some implementations, the curvature c of the temporary target trajectory 2_temp can be calculated as:

[0079]

[0080] Among them, c 2_tc Indicates the curvature of the centerline of the target lane.

[0081] In addition, in some implementations, the curvature change rate c of the temporary target trajectory is 3_temp can be set to be equal to the rate of change of curvature of the centerline of the target lane, that is:

[0082] C 3_temp =c 3_tc

[0083] It should be understood that other ways of calculating each of the above coefficients are possible.

[0084] According to some implementations of the present disclosure, in the calculation of the heading angle of the temporary target trajectory, p Time The value of can be obtained by looking up the table using the lateral distance from the vehicle to the centerline of the target lane. In some implementations, p Time The value of takes into account the driver's habit of manually changing lanes, and can increase as the lateral distance from the vehicle 100 to the center line 140 of the target lane 120 decreases, and the two are anti-correlated. Through such a setting, overshoot can be effectively avoided. In some examples, the anti-correlation can be nonlinear.

[0085] Looking at step 240 again, the calculated temporary target trajectory will be provided as input to the lane centering function. That is, the input normally provided to the lane centering function of the vehicle 100 should be the center line 130 of the lane 110 in which the vehicle is currently located, but according to the mechanism proposed in the present disclosure, the input is replaced by the temporary target trajectory calculated by step 230, and accordingly, the lane centering function uses this temporary target trajectory as the target center line to control the movement of the vehicle 100.

[0086] In some implementations, the lane centering function can calculate errors based on the temporary target trajectory and the driving trajectory of the vehicle 100 (the vehicle 100 can be considered to be moving in a fixed circle, so its driving trajectory can be simplified to a quadratic curve containing only quadratic coefficients, but the present disclosure is not limited to this), including lateral errors and heading angle errors, and eliminate the errors by using control algorithms such as PID or LQR, and output corresponding control signals (including but not limited to steering requests) to the relevant control units of the vehicle to control the vehicle. The specific operations of the lane centering function will not be repeated here.

[0087] Next, we discuss the control flow in some other scenarios during the entire automatic lane change process. Figure 1 The initial position shown in the figure is driven to a position between the center line 140 and the lane line 150 in the lane 120 through the automatic lane change mechanism. For example, assume that the vehicle 100 has just crossed the lane line 150 between the lanes 110 and the lane 120, but is still far away from the center line 140.

[0088] In this case, when executing step 210 in method 200, by Figure 3 The current lane determined in step 310 is no longer lane 110, but lane 120. Accordingly, the judgment result of step 320 will be "no", that is, the current lane 120 is no longer the original lane 110 as the starting point of the lane change, so the exemplary operation 300 will turn to execute step 340, that is, the center line 140 of the current lane 120 is directly used as the center line of the target lane.

[0089] Next, step 220 of method 200 is executed. At this moment, the lateral distance between the vehicle 100 and the center line 140 of the target lane 120 may still not be less than the distance threshold (e.g., 0.3 meters), and the judgment result of step 220 is still "no", so the next steps 230 and 240 are executed. After that, the subsequent cycle process will continue.

[0090] Consider again the case where the vehicle 100 has further traveled from the aforementioned position to a position in the lane 120 close to the center line 140 through the automatic lane change mechanism. For example, assume that the lateral distance between the vehicle 100 and the center line 140 is only 0.25 meters at this moment. In this case, step 210 of the method 200 continues to regard the center line 140 of the current lane 120 as the center line of the target lane. When executing step 220, the judgment result of this step will be "yes", that is, the lateral distance between the vehicle 100 and the center line 140 is less than the distance threshold of 0.3 meters, so the method 200 will jump out of the loop and end execution.

[0091] According to some implementations of the present disclosure, the distance threshold may be related to the vehicle control capability of the lane centering function of the vehicle 100. When the lateral distance between the vehicle 100 and the center line 140 of the target lane 120 is less than the distance threshold, the execution of the method 200 may be exited, and the lane centering function may be directly handed over to continue to control the vehicle according to its normal operating logic.

[0092] In addition, according to some implementations of the present disclosure, the lane centering function can be based on a dual preview point mechanism, wherein the lateral error between the temporary target trajectory line and the vehicle's driving trajectory line is calculated at a near preview point (e.g., a preset distance in front of the vehicle), and the heading angle error between the temporary target trajectory line and the vehicle's driving trajectory line is calculated at a far preview point (e.g., the position of the vehicle after it has traveled a preset preview time).

[0093] See next Figure 4 , which shows examples of heading angle errors according to some implementations of the present disclosure. The horizontal direction in the diagram represents the lateral distance from the vehicle to the center line of the target lane (in meters), and the vertical direction represents the heading angle error (in degrees) calculated by the lane centering keeping function according to the automatic lane changing mechanism proposed in the present disclosure. It should be understood that the specific values ​​in this figure are given for illustrative purposes only. It can be seen that the heading angle error, which is one of the bases of the vehicle control signal output by the lane centering keeping function, is large at the beginning of the automatic lane changing process; and as the lateral distance from the vehicle to the center line of the target lane shortens, the heading angle error gradually converges and eventually becomes 0, which also ensures that there will be no overshoot during the lane changing process.

[0094] Reference below Figure 5 , which shows a block diagram of an exemplary apparatus 500 according to some implementations of the present disclosure. The apparatus 500 may be implemented, for example, in Figure 1 The vehicle 100 shown is used to implement the mechanism described herein for implementing automatic lane change based on a lane centering function.

[0095] like Figure 5As shown, the device 500 may include a module 510, which is used to determine the center line of the target lane as the lane change target according to the current lane where the vehicle is located. The device 500 may also include a module 520, which is used to determine whether the lateral distance from the vehicle to the center line of the target lane is less than a distance threshold. The device 500 may also include a module 530, which is used to calculate a temporary target trajectory line according to the center line of the target lane and the longitudinal speed of the vehicle in response to determining that the lateral distance from the vehicle to the center line of the target lane is not less than the distance threshold, wherein the temporary target trajectory line deviates from the specified step length relative to the vehicle in the lateral direction. In addition, the device 500 may also include a module 540, which is used to provide the temporary target trajectory line as an input to the lane centering keeping function of the vehicle, wherein the lane centering keeping function uses the temporary target trajectory line as the target center line to control the vehicle movement.

[0096] In some implementations, the apparatus 500 may further include additional modules for performing other operations described in the specification, such as combining Figure 2 A flowchart of an exemplary method 200 of Figure 3 The exemplary operation 300 of the present invention is described in detail with reference to the flowchart of the exemplary operation 300 and its variations. In addition, in some implementations, the various modules of the apparatus 500 may be combined or split depending on actual needs. It will be appreciated by those skilled in the art that the exemplary apparatus 500 may be implemented using software, hardware, firmware, or any combination thereof.

[0097] Figure 6 600 according to some implementations of the present disclosure. The computing device 600 may be implemented, for example, in Figure 1 The vehicle 100 shown is used to implement the mechanism described herein for implementing automatic lane change based on a lane centering function.

[0098] like Figure 6 As shown, the computing device 600 may include at least one processor 610. The processor 610 may include any type of general-purpose processing unit, special-purpose processing unit, core, circuit, controller, etc. In addition, the computing device 600 may also include a memory 620. The memory 620 may include any type of medium that can be used to store data. In some implementations, the memory 620 is configured to store instructions that, when executed, cause the at least one processor 610 to perform the operations described herein, for example, in conjunction with Figure 2 A flowchart of an exemplary method 200 of Figure 3 Various operations are described with reference to a flowchart of exemplary operations 300 and variations thereof.

[0099] In addition, in some implementations, the computing device 600 is also equipped with a communication interface that can support various types of wired / wireless communication protocols to communicate with a communication network (e.g., Figure 1 Communicates with a communication bus within the vehicle 100 shown in FIG.

[0100] Those skilled in the art will appreciate that the above description of the structure of the computing device 600 is merely exemplary and not restrictive, and devices with other structures are also feasible as long as they can be used to implement the functions described herein.

[0101] Various implementations of the present disclosure may include or operate multiple components, parts, units, modules, instances or mechanisms, which may be implemented in hardware, software, firmware, or any combination thereof. Examples of hardware may include, but are not limited to: devices, processors, microprocessors, circuits, circuit elements (e.g., transistors, resistors, capacitors, inductors, etc.), integrated circuits, application specific integrated circuits (ASICs), programmable logic devices (PLDs), digital signal processors (DSPs), field programmable gate arrays (FPGAs), storage units, logic gates, registers, semiconductor devices, chips, microchips, chipsets, etc. Examples of software may include, but are not limited to: software components, programs, applications, computer programs, application programs, system programs, machine programs, operating system software, middleware, software modules, routines, subroutines, functions, methods, processes, software interfaces, application programming interfaces (APIs), instruction sets, computer codes, computer code segments, words, values, symbols, or any combination thereof. Determining whether an implementation is implemented using hardware, software, and / or firmware can vary depending on a variety of factors, such as desired computational rates, power levels, thermal tolerances, processing cycle budgets, input data rates, output data rates, memory resources, data bus speeds, and other design or performance constraints as desired for a given implementation.

[0102] Some implementations described herein may include articles of manufacture. Articles of manufacture may include storage media. Examples of storage media may include volatile and non-volatile, removable and non-removable media implemented by any method or technology to store information (e.g., computer-readable instructions, data structures, program modules, or other data). Storage media may include, but are not limited to: random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk (CD), digital versatile disk (DVD) or other optical storage, cassette, tape, disk storage or other magnetic storage device, or any other medium capable of storing information. In some implementations, articles of manufacture may store executable computer program instructions that, when executed by one or more processing units, cause the processing units to perform the operations described herein. Executable computer program instructions may include any suitable type of code, for example, source code, compiled code, interpreted code, executable code, static code, dynamic code, and the like. Executable computer program instructions may be implemented using any suitable high-level, low-level, object-oriented, visual, compiled and / or interpreted programming language.

[0103] Some exemplary implementations of the present disclosure are described below.

[0104] Example 1 may include a method for implementing automatic lane change based on a lane centering function, the method comprising: determining a center line of a target lane as a lane change target based on a current lane in which a vehicle is located; determining whether a lateral distance from the vehicle to the center line of the target lane is less than a distance threshold; in response to determining that the lateral distance from the vehicle to the center line of the target lane is not less than the distance threshold, calculating a temporary target trajectory based on the center line of the target lane and the longitudinal speed of the vehicle, wherein the temporary target trajectory deviates laterally from the vehicle by a specified step size; and providing the temporary target trajectory as input to a lane centering function of the vehicle, wherein the lane centering function controls the vehicle movement using the temporary target trajectory as the target center line.

[0105] Example 2 may include the subject matter of Example 1, wherein the steps of the method are iteratively performed until it is determined that the lateral distance of the vehicle to the centerline of the target lane is less than the distance threshold.

[0106] Example 3 may include the subject matter described in any of the foregoing examples, wherein determining the center line of a target lane as a lane change target based on a current lane in which a vehicle is located comprises: determining the current lane in which the vehicle is located; determining whether the current lane is the original lane serving as a starting point for lane change; in response to a yes result of the determination, obtaining the center line of the target lane by shifting the center line of the current lane laterally by a specified size related to the lane width; in response to a no result of the determination, using the center line of the current lane as the center line of the target lane.

[0107] Example 4 may include the subject matter of any of the preceding examples, wherein the centerline of the target lane is represented by a cubic curve, and wherein the lateral deviation c of the temporary target trajectory is 0_temp is calculated as:

[0108] c 0_temp =signum(c 0_tc )×p Step

[0109] Among them, c 0_tc represents the lateral deviation of the center line of the target lane, p Step represents the specified step size, and signum() is the sign function.

[0110] Example 5 may include the subject matter of any of the preceding examples, wherein the heading angle c of the temporary target trajectory is 1_temp is calculated as:

[0111]

[0112] Among them, c 1_tc represents the heading angle of the center line of the target lane, v represents the longitudinal speed of the vehicle, and p Time Represents the time parameter.

[0113] Example 6 may include the subject matter of any of the preceding examples, wherein the time parameter is inversely correlated with a lateral distance of the vehicle from a centerline of the target lane.

[0114] Example 7 may include the subject matter of any of the preceding examples, wherein the specified step size is a fixed value selected from a range of 0.15 meters to 0.2 meters.

[0115] Example 8 may include the subject matter of any of the preceding examples, wherein the specified step size is variable depending on a lateral distance of the vehicle from a centerline of the target lane.

[0116] Example 9 may include the subject matter of any of the preceding examples, wherein the lane centering function employs a dual preview point mechanism, wherein the lateral error is calculated at a near-end preview point and the heading angle error is calculated at a far-end preview point.

[0117] Example 10 may include a device for implementing an automatic lane change function based on a lane centering function, the device comprising: a module for determining the center line of a target lane as a lane change target based on a current lane in which a vehicle is located; a module for determining whether a lateral distance from the vehicle to the center line of the target lane is less than a distance threshold; a module for calculating a temporary target trajectory line based on the center line of the target lane and the longitudinal speed of the vehicle in response to determining that the lateral distance from the vehicle to the center line of the target lane is not less than the distance threshold, wherein the temporary target trajectory line deviates laterally from the vehicle by a specified step size; and a module for providing the temporary target trajectory line as an input to the lane centering function of the vehicle, wherein the lane centering function uses the temporary target trajectory line as the target center line to control the vehicle movement.

[0118] Example 11 may include a computing device comprising: at least one processor; and a memory coupled to the at least one processor and used to store instructions, wherein the instructions, when executed by the at least one processor, cause the at least one processor to perform the method described in any one of the aforementioned Examples 1-9.

[0119] Example 12 may include a computer-readable storage medium having instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to perform the method described in any one of the foregoing Examples 1-9.

[0120] Example 13 may include a computer program product comprising instructions that, when executed by at least one processor, cause the at least one processor to perform the method of any of the foregoing Examples 1-9.

[0121] What has been described above includes examples of the disclosed architecture. It is certainly not possible to describe every conceivable combination of components and / or methods, but those skilled in the art will appreciate that many other combinations and permutations are possible. Therefore, the novel architecture is intended to encompass all such substitutions, modifications, and variations that fall within the spirit and scope of the appended claims.

Claims

1. A method for implementing automatic lane change based on a lane centering function, the method comprising: Determine the center line of a target lane as a lane change target according to the current lane in which the vehicle is located; Determining whether a lateral distance from the vehicle to a center line of the target lane is less than a distance threshold; In response to determining that the lateral distance from the vehicle to the centerline of the target lane is not less than the distance threshold, calculating a temporary target trajectory based on the centerline of the target lane and the longitudinal speed of the vehicle, wherein the temporary target trajectory deviates laterally from the vehicle by a specified step size; and The temporary target trajectory is provided as input to a lane centering function of the vehicle, wherein the lane centering function controls the vehicle motion with the temporary target trajectory as a target centerline.

2. The method according to claim 1, wherein: The steps of the method are iteratively performed until it is determined that the lateral distance of the vehicle to the center line of the target lane is less than the distance threshold.

3. The method according to claim 1, wherein: Determining the center line of the target lane as the lane change target according to the current lane where the vehicle is located includes: Determining a current lane of the vehicle; Determining whether the current lane is the original lane serving as the starting point of lane change; In response to a result of the determination being yes, obtaining a center line of the target lane by laterally shifting the center line of the current lane by a specified amount related to a lane width; In response to a negative result of the determination, the center line of the current lane is used as the center line of the target lane.

4. The method according to claim 3, wherein: The center line of the target lane is represented by a cubic curve, and the lateral deviation c of the temporary target trajectory is 0_temp is calculated as: c 0_temp =sign(c 0_tc )×p Step Among them, c 0_tc represents the lateral deviation of the center line of the target lane, p Step represents the specified step size, and signum() is the sign function.

5. The method according to claim 4, wherein: The heading angle c of the temporary target trajectory 1_temp is calculated as: Among them, c 1_tc represents the heading angle of the center line of the target lane, v represents the longitudinal speed of the vehicle, and p Time Represents the time parameter.

6. The method according to claim 5, wherein: The time parameter is inversely correlated with a lateral distance of the vehicle from a centerline of the target lane.

7. The method according to claim 4, wherein: The specified step length is a fixed value selected from the range of 0.15 meters to 0.2 meters.

8. The method according to claim 4, wherein: The specified step size is variable depending on a lateral distance of the vehicle from a centerline of the target lane.

9. The method according to claim 1, wherein: The lane centering function adopts a dual preview point mechanism, in which the lateral error is calculated at the near-end preview point and the heading angle error is calculated at the far-end preview point.

10. A device for implementing an automatic lane change function based on a lane centering function, the device comprising: A module for determining a center line of a target lane as a lane change target according to a current lane in which the vehicle is located; A module for determining whether a lateral distance from the vehicle to the center line of the target lane is less than a distance threshold; module for calculating a temporary target trajectory based on the centerline of the target lane and the longitudinal speed of the vehicle in response to determining that the lateral distance of the vehicle to the centerline of the target lane is not less than the distance threshold, wherein the temporary target trajectory is laterally deviated from the vehicle by a specified step size; and Means for providing the temporary target trajectory as input to a lane centering function of the vehicle, wherein the lane centering function controls the vehicle motion using the temporary target trajectory as a target centerline.

11. A computing device, the computing device comprising: at least one processor; as well as A memory, coupled to the at least one processor and configured to store instructions, wherein when the instructions are executed by the at least one processor, the at least one processor is enabled to perform the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having instructions stored thereon, wherein when the instructions are executed by at least one processor, the at least one processor executes the method according to any one of claims 1-9.

Images