A method, device, and storage medium for implementing lane centering

Abstract

The present invention relates to a method, device and storage medium for realizing lane centering. The method includes identifying lane lines and lane boundaries of the road where the vehicle itself is located during driving, and planning the lateral trajectory of the vehicle itself based on the lane lines and lane boundaries; adding a lateral offset to the lateral trajectory planning based on the pose information of the vehicle itself, and dynamically correcting the lateral offset according to the current curb width and highway grade; re-planning the lateral trajectory of the vehicle itself according to the corrected lateral offset, and centering the vehicle itself according to the re-planned lateral trajectory. The present invention combines the curb width, road curvature and driving habits to plan the lateral trajectory, and dynamically adjusts according to the real-time measured values, so as to reduce the psychological pressure of the passengers and improve the sense of security when the lane centering function is turned on.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle assisted driving, and particularly relates to a method, device and storage medium for realizing lane centering. Background Art

[0002] The advanced assisted driving lane centering function can keep the vehicle in the middle lane or the middle of the lane. However, in some scenarios, driving in the center does not meet the expectations of normal drivers. For example, when driving in the leftmost or rightmost lane of a highway and there are guardrails / median strips / curbs on both sides of the road, normal drivers will drive on the side away from the guardrail / median strip / curb for safety reasons due to psychological factors. This is especially obvious when turning. The current lane centering function fails to optimize the corresponding strategy in combination with the driver's expectations. In such working conditions, it still controls the vehicle to drive in the center, which puts great psychological pressure on the driver and even causes panic in extreme working conditions. Summary of the Invention

[0003] In order to combine the driver's expectations, optimize the lane centering strategy and reduce the driver's psychological pressure, in the first aspect of the present invention, a method for realizing lane centering is provided, including: identifying the lane lines and lane boundaries of the road where the vehicle is located during driving, and planning the lateral trajectory of the vehicle based on the lane lines and lane boundaries; adding a lateral offset to the lateral trajectory planning based on the pose information of the vehicle itself, and dynamically correcting the lateral offset according to the current curb width and highway grade; re-planning the lateral trajectory of the vehicle itself according to the corrected lateral offset, and centering the vehicle according to it.

[0004] In some embodiments of the present disclosure, adding a lateral offset to the lateral trajectory planning based on the pose information of the vehicle itself, and dynamically correcting the lateral offset according to the current curb width and highway grade includes: determining an initial value of the offset; determining a first correction coefficient according to the current curb width of the road; determining a second correction coefficient according to the current steering curvature of the vehicle itself; and correcting the lateral offset based on the first correction coefficient and the second correction coefficient.

[0005] Further, determining the first correction coefficient according to the current curb width of the road includes: establishing a first mapping table between the first correction coefficient and the curb width; determining the width of the road shoulder according to the grade of the highway; and determining the first correction coefficient based on the grade of the highway and the first mapping table.

[0006] Further, determining the second correction coefficient according to the current steering curvature of the vehicle itself includes: establishing a second mapping table between the second correction coefficient and the steering curvature; calculating the current steering curvature of the vehicle itself, and matching it with the second mapping table to determine the second correction coefficient.

[0007] Further, the value of the first correction coefficient is within the interval (0, 1], and the curb width ranges from 0.25 m to 0.75 m.

[0008] In the above embodiment, the lateral trajectory planning of the own vehicle with respect to the lane line and the lane boundary is achieved by the following method:

[0009] ,

[0010] where x and y respectively represent the ordinate and abscissa of the own vehicle in the vehicle coordinate system of the own vehicle, represents the lateral position at the origin of the vehicle coordinate system of the own vehicle, , and are all preset trajectory coefficients.

[0011] In a second aspect of the present invention, there is provided a lane centering implementation device, including: an identification module, configured to identify the lane line and the lane boundary of the road where the own vehicle is located during driving, and perform lateral trajectory planning for the own vehicle based on the lane line and the lane boundary; a correction module, configured to add a lateral offset to the lateral trajectory planning based on the pose information of the own vehicle, and dynamically correct the lateral offset according to the current curb width and the highway grade; a centering module, configured to re-plan the lateral trajectory of the own vehicle according to the corrected lateral offset, and center the own vehicle according to it.

[0012] Further, the correction module includes: a determination unit, configured to determine an initial value of the offset; a first correction unit, configured to determine a first correction coefficient according to the current curb width of the road, and determine a second correction coefficient according to the steering curvature of the own vehicle currently; a second correction unit, configured to correct the lateral offset based on the first correction coefficient and the second correction coefficient.

[0013] In a third aspect of the present invention, there is provided an electronic device, including: one or more processors; a storage device, configured to store one or more programs, and when the one or more programs are executed by the one or more processors, enable the one or more processors to implement a lane centering implementation method provided by the present invention in the first aspect.

[0014] In a fourth aspect of the present invention, there is provided a computer-readable medium, on which a computer program is stored, wherein when the computer program is executed by a processor, a lane centering implementation method provided by the present invention in the first aspect is implemented.

[0015] The beneficial effects of the present invention are as follows: In view of the problem that when the lane centering function is driving in the outermost lane, there is a risk of rubbing against the road boundary, which causes panic among the driver and passengers, etc., the present invention provides a method for realizing lane centering, including: identifying the lane lines and lane boundaries of the road where the vehicle itself is located during driving, and planning the lateral trajectory of the vehicle itself based on the lane lines and lane boundaries; adding a lateral offset to the lateral trajectory planning based on the pose information of the vehicle itself, and dynamically correcting the lateral offset according to the current curb width and highway grade; re-planning the lateral trajectory of the vehicle itself according to the corrected lateral offset, and centering the vehicle itself according to it. That is, using the lane recognition system to obtain the curb width and road curvature to calculate the lateral trajectory offset, and then combining the current position of the vehicle in the lane to re-plan the lateral trajectory, simulating the driving habits of normal drivers, so as to reduce the psychological pressure of the driver and passengers when the lane centering function is turned on and improve the sense of security. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 An example road for multiple aspects in some embodiments of the present invention;

[0017] Figure 2 A schematic diagram of the basic process of the lane centering implementation method in some embodiments of the present invention;

[0018] Figure 3 A geometric schematic diagram between the lane lines, lanes, and curbs of the road;

[0019] Figure 4 A schematic diagram of lane centering of the vehicle in the case of obstacle avoidance in some embodiments of the present invention;

[0020] Figure 5 A schematic diagram of the specific process of the lane centering implementation method in some embodiments of the present invention;

[0021] Figure 6 A schematic diagram of the structure of the lane centering implementation device in some embodiments of the present invention;

[0022] Figure 7 A schematic diagram of the structure of an electronic device in some embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0024] Refer to Figures 1 to 3, in the first aspect of the present invention, a method for realizing lane centering is provided, including: S100. Identifying the lane lines and lane boundaries of the road where the vehicle itself is located during driving, and planning the lateral trajectory of the vehicle itself based on the lane lines and lane boundaries; S200. Adding a lateral offset to the lateral trajectory planning based on the pose information of the vehicle itself, and dynamically correcting the lateral offset according to the current curb width and highway grade; S300. Re-planning the lateral trajectory of the vehicle itself according to the corrected lateral offset, and centering the vehicle itself according to it.

[0025] It should be understood that, without loss of generality, a road generally includes shoulders, curb strips (curbs) and medians; Shoulder: It refers to a strip part with a certain width located between the outer edge of the carriageway and the roadbed edge (including the hard shoulder and the protective shoulder), which is used to maintain the function of the carriageway and for temporary parking, and serves as the lateral support of the road surface. Curb strip: A narrow strip of road surface at the left and right edges of the carriageway, which is a part of the shoulder or median, and appears as a guardrail / separator / curb on different roads. Median: The highway median consists of a separator and a curb strip. The separator is demarcated by facilities such as curb lines and plays a role in separating oncoming traffic in terms of structure; the curb strip plays a role in guiding the line of sight and increasing the lateral clearance, so as to improve the driving speed, driving safety and comfort. In particular, when a vehicle turns through multiple lanes, such as a two-lane or three-lane turn, left or right, the driver often takes a shortcut and crosses the lane boundary. For example, Figure 1 FIG. 100 shows a road section 100 where vehicles 101 and 102 pass through a two-lane left turn 160 in the inner lane 161 and the outer lane 162 respectively. Vehicle 102 passing through the outer lane 162 straddles into the inner lane 161 and enters the path of vehicle 101 passing through the inner lane 161. In order to avoid hitting vehicle 102, vehicle 101 may be forced to adjust its trajectory. Vehicles such as vehicle 101 are usually cut-off or pushed out of their current trajectories by vehicles driving in adjacent lanes. Since autonomous vehicles can be programmed to follow the trajectory within the lane where the vehicle is located, these problems are magnified for autonomous vehicles. Thus, during the turn of an autonomous vehicle passing through a multi-lane turn, when the autonomous vehicle is "cut-off" or "pinched" by another vehicle, an avoidance action may be required. Such an avoidance action may cause discomfort or insecurity to the passengers of the autonomous vehicle.

[0026] To address these issues, when an autonomous vehicle makes a multi-lane turn, its actions and trajectory (the embodiments of the present invention mainly consider the lateral trajectory) can be adjusted. The trajectory can be adjusted based on the position of the vehicle relative to other vehicles or based on historical data of the vehicle making a multi-lane turn. In this regard, when making a multi-lane turn, the autonomous vehicle can be in multiple positions relative to other vehicles. For example, it can be the first vehicle in a row of vehicles, the last vehicle in a row of vehicles, or in the middle of the vehicles. For example, when the autonomous vehicle is positioned at the head of a row of vehicles, the trajectory of the autonomous vehicle can be adjusted so that it can follow an alternative trajectory based on historical data corresponding to the previous path taken by the vehicle when making a multi-lane turn. In the case where the autonomous vehicle is positioned in the middle or behind other vehicles, the trajectory of the autonomous vehicle can be adjusted so that it follows the trajectory of the vehicle positioned in front. The historical data can include the previous paths taken by the autonomous vehicle or other vehicles when making a multi-lane turn, and this historical data can be monitored and used to change the nominal trajectory of the autonomous vehicle. Based on this historical data, an alternative trajectory can be followed instead of the nominal trajectory of the autonomous vehicle to more closely resemble the previous trajectory of the vehicle passing through the turn. In some cases, the alternative trajectory can be restricted to prevent the autonomous vehicle from deviating too far from a safe operating trajectory. In the case where the vehicle passes through a lane adjacent to the autonomous vehicle, the autonomous vehicle can adjust its trajectory so that it staggers relative to the adjacent vehicle to increase its visibility to the driver of the adjacent vehicle. In other words, the autonomous vehicle can continuously position itself so that it is positioned between the vehicles in the adjacent lane, enabling the vehicles in the adjacent lane to see the autonomous vehicle. It can be seen that in order to relieve the psychological pressure of the driver while driving, the curb width should be as large as possible, so it is necessary to adjust the lateral offset according to the actual driving situation.

[0027] The features described herein allow for improved and safer driving for autonomous or semi-autonomous driving that only involves lane centering (not limited to straight or curved roads, single or multi-lane). In this regard, the lane centering described herein provides more comfortable turning conditions for the passengers of the autonomous vehicle because avoidance maneuvers such as emergency braking or sharp turning can be avoided. In addition, the autonomous vehicle can be positioned so that it is more visible to surrounding vehicles, reducing the risk that the driver cannot see the autonomous vehicle when making a multi-lane turn. Additionally, the movement of the autonomous vehicle making a multi-lane turn may be more typical for a human driver, enabling the drivers of surrounding vehicles to more easily predict the movement of the autonomous vehicle.

[0028] In the embodiment S100 of the present invention, the lateral trajectory planning of the own vehicle with respect to the lane lines and lane boundaries is achieved by the following method:

[0029] ,

[0030] where x and y respectively represent the ordinate and abscissa of the host vehicle in the host vehicle coordinate system, represents the lateral position at the origin of the host vehicle coordinate, , and are both preset trajectory coefficients. corresponds to the lateral position at the origin of the host vehicle coordinate, corresponds to the heading angle at the origin of the host vehicle coordinate. It can be understood that the above lateral trajectory planning is expressed by taking a cubic polynomial as an example; optionally, the lateral trajectory planning can be expressed by using a multiple polynomial, and the coefficients (preset trajectory coefficients) of each term in the polynomial are determined to more precisely control the lateral trajectory planning.

[0031] Schematically, Figure 3 shows the geometric relationship among several lanes, lane lines and road edges in a road. The road edge usually appears as a median strip or the edge of the road, and the lane line usually coincides with the median strip or guardrail. Define the road edge width dy, where dy represents the lateral distance between the lane boundary and the nearest lane line. When dy is smaller, the psychological pressure of the driver driving is greater, and at this time, the lateral offset needs to be amplified.

[0032] In view of this, in step S200 of some embodiments of the present disclosure, adding a lateral offset to the lateral trajectory planning based on the pose information of the host vehicle and dynamically correcting the lateral offset according to the current road edge width and highway grade includes: S201. Determining the initial value of the offset; determining a first correction coefficient according to the current road edge width; S202. Determining a second correction coefficient according to the current steering curvature of the host vehicle; S203. Correcting the lateral offset based on the first correction coefficient and the second correction coefficient.

[0033] Therefore, a lateral offset correction coefficient γ related to the curvature ρ is defined in the above S100. Here, the lateral distance dy between the lane boundary and the nearest lane line and the road curvature can both be identified and calculated by a front view camera. The calculation formula of the lateral offset is as follows:

[0034] ,

[0035] where d0 is the value corresponding to the offset without any correction, which is a calibratable quantity, and the typical value is 0.2m, and it should not be too large.

[0036] Further, in step S201, the determining the first correction coefficient according to the curb width of the current road includes: establishing a first mapping table between the first correction coefficient and the curb width; determining the width of the curb strip according to the grade of the highway; and determining the first correction coefficient based on the grade of the highway and the first mapping table.

[0037] Specifically, the mapping table corresponding to the offset correction coefficient k and the curb width dy is as follows:

[0038]

[0039] Among them, the value of the curb width dy can be set with reference to the width of the curb strip of the national highway. As shown in the following table, it can be seen that the width of the curb strip of most highways is between 0.25m and 0.75m. Therefore, the value of dy can be between 0 and 1, which can basically cover the working conditions of most roads.

[0040]

[0041] The setting principle of the offset correction coefficient k is as follows:

[0042] When dy is 0, it means that the risk of the driver hitting the road boundary when driving in the outermost lane is very high. At this time, the correction coefficient k takes the maximum value of 1; when dy is 1, it means that the risk of the driver hitting the road boundary when driving in the outermost lane is very small. In order to ensure the lane centering performance, the lateral trajectory is not offset at this time, and the correction coefficient k takes the minimum value of 0; when the value of dy is between 0 and 1, the value of K can be calibrated in combination with the actual experience of the driver and passengers. The trend is that as dy increases, the value of K should gradually decrease.

[0043] Further, in step S202, the determining the second correction coefficient according to the steering curvature of the current own vehicle includes: establishing a second mapping table between the second correction coefficient and the steering curvature; calculating the steering curvature of the current own vehicle, and matching it with the second mapping table to determine the second correction coefficient.

[0044] Specifically, the mapping table corresponding to the offset correction coefficient γ and the curvature ρ is as follows:

[0045]

[0046] The value of the rate ρ can be set in combination with the radius of the bend of the actual road and can refer to the above mapping table. The setting principle of the offset correction coefficient γ is as follows:

[0047] When the curvature ρ is 0, it indicates that the road is straight at this time, and the offset correction coefficient γ does not need to be amplified and takes a value of 1. As the value of ρ increases, the bend becomes sharper. At this time, when the driver drives in the outermost lane, the risk of rubbing against the road boundary increases, and the value of the offset correction coefficient γ needs to be appropriately amplified. Specifically, it needs to be calibrated in combination with the actual experience of the driver and passengers.

[0048] In S201 and S202 of the above embodiments, the value of the first correction coefficient is within the range of [0, 1], and the value of the curb width is within 0.25 m to 0.75 m.

[0049] It can be understood that Figure 3 is a schematic diagram of the vehicle lane change (lane centering) scenario when there is no obstacle vehicle in front and there is no obstacle vehicle in the target lane either, without considering the problems of curves and obstacle avoidance.

[0050] Refer to Figure 4 , there is a vehicle driving on the target lane, and the problem of vehicle obstacle avoidance needs to be considered. In practice, the variable range of the longitudinal speed and acceleration during the vehicle driving process is larger than that of the lateral direction, and from the perspective of driving comfort, the longitudinal speed change is more acceptable than the lateral speed change. Therefore, collision avoidance can be achieved by increasing the degree of the longitudinal (x - direction) polynomial. The dashed box (In the symbol, the subscript 0 represents vehicle No. 0, and the superscript 1 represents the first moment, that is, the completion moment. The corresponding superscript 0 represents the initial moment, and the same applies hereinafter) represents the target position of the lane - changing vehicle. Len represents the length of the vehicle itself, SS represents the distance between vehicles, and VC1·tlc represents the distance experienced during lane change.

[0051] Refer to Figure 4 and Figure 5 , considering that during the vehicle driving process, it is not like the standard one - way 3 - lane in Figure 2 , so it is necessary to judge the position of the vehicle during driving, that is, the relationship with the curb. For example, when the road is a two - way two - lane road, the curb is located on one side (left or right) of the lane line. At this time, lane centering degenerates into a lane - changing process from the lane close to the curb to the lane far from the curb.

[0052] In view of this, in a specific embodiment of the present invention, step S100 is implemented by a lane recognition system, and step S200 is implemented by the lateral control module and the vehicle steering actuator of the vehicle; its specific steps include:

[0053] Step 1: The lane recognition system calculates the offset d according to the curb width dy and the curvature ρ: ,

[0054] Step 2: The intelligent control system (ECU) in the intelligent driving vehicle determines the lane where the vehicle is located according to the current pose information:

[0055] If it is in the leftmost lane, re-plan the trajectory

[0056] ; If it is in the middle lane, re-plan the trajectory ; If it is in the leftmost lane, re-plan the trajectory

[0057] ;

[0058] Step 3: Finally, the lateral control module and the vehicle steering actuator of the vehicle achieve lane centering.

[0059] Embodiment 2

[0060] Reference Figure 6 According to this, the second aspect of the present invention provides a lane centering implementation device 1, including: an identification module 11, configured to identify the lane lines and lane boundaries of the road where the vehicle is located during driving, and plan the lateral trajectory of the vehicle based on the lane lines and lane boundaries; a correction module 12, configured to add a lateral offset to the lateral trajectory planning based on the pose information of the vehicle itself, and dynamically correct the lateral offset according to the current curb width and highway grade; a centering module 13, configured to re-plan the lateral trajectory of the vehicle itself according to the corrected lateral offset, and perform lane centering on the vehicle itself according to it.

[0061] Further, the correction module 12 includes: a determination unit, configured to determine the initial value of the offset; a first correction unit, configured to determine a first correction coefficient according to the curb width of the current road; determine a second correction coefficient according to the steering curvature of the current vehicle itself; a second correction unit, configured to correct the lateral offset based on the first correction coefficient and the second correction coefficient.

[0062] In addition, in this embodiment, in the operation of the vehicle control ECU to control the vehicle, all accelerator operations, brake operations, and steering wheel operations, which are operations related to the behavior of the vehicle, are described as autonomous driving assistance (assisted driving) for automatically driving regardless of the user's driving operation. However, the autonomous driving assistance can also be set as at least one of the accelerator operation, brake operation, and steering wheel operation, which are operations related to the behavior of the vehicle, in the operation of the vehicle control ECU to control the vehicle. On the other hand, the manual driving performed by the user's driving operation is described as all accelerator operations, brake operations, and steering wheel operations, which are operations related to the behavior of the vehicle, in the operation of the user to control the vehicle.

[0063] In addition, in the present embodiment, the lane centering program is configured to be executed by the navigation device 1, but it may also be configured to be executed by the vehicle control ECU. In this case, the vehicle control ECU is configured to acquire the current position, map information, traffic information, etc. of the vehicle from the navigation device.

[0064] In addition, the present invention can be applied to devices having a route search function in addition to the navigation device. For example, it can also be applied to mobile phones, smartphones, tablet terminals, personal computers, etc. (hereinafter referred to as mobile terminals, etc.). In addition, it can also be applied to a system composed of a server and mobile terminals, etc. In this case, each step of the above-mentioned lane centering program ( Figure 2 ) can also be configured to be implemented by either the server or mobile terminals, etc. However, when applying the present invention to mobile terminals, etc., it is necessary to connect a vehicle capable of performing autonomous driving assistance and the mobile terminals, etc. in a communicable manner (regardless of wired or wireless). In addition, the embodiments of concretizing the autonomous driving assistance system according to the present invention have been described above, but the autonomous driving assistance system can also have the following configuration, and in this case, the following effects are achieved.

[0065] Embodiment 3

[0066] Reference Figure 7 , in the third aspect of the present invention, there is provided an electronic device, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enabling the one or more processors to implement the method of the first aspect of the present invention.

[0067] The electronic device 500 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to the programs stored in the read-only memory (ROM) 502 or the programs loaded from the storage device 508 into the random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0068] Generally, the following devices can be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a hard disk, etc.; and a communication device 509. The communication device 509 can allow the electronic device 500 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 7An electronic device 500 with various devices is shown, but it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had. Figure 7 Each block shown in [it] may represent a device or, as needed, multiple devices.

[0069] In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, an embodiment of the present disclosure includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program contains program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by a processing device 501, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed. It should be noted that the computer-readable medium described in the embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. And in the embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0070] The above computer-readable medium may be included in the above electronic device; or may exist separately without being assembled into the electronic device. The above computer-readable medium carries one or more computer programs, and when the above one or more programs are executed by the electronic device, the electronic device is caused to:

[0071] Computer program code for performing the operations of the embodiments of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, Python, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, by connecting through the Internet using an Internet service provider).

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0073] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for realizing lane centering, characterized in that, Including: Identifying the lane lines and lane boundaries of the road where the own vehicle is located during driving, and planning the lateral trajectory of the own vehicle based on the lane lines and lane boundaries; Based on the pose information of the own vehicle, adding a lateral offset to the lateral trajectory planning, and dynamically correcting the lateral offset according to the current curb width and highway grade; Re-planning the lateral trajectory of the own vehicle according to the corrected lateral offset, and centering the own vehicle in the lane according to it; The step of, based on the pose information of the own vehicle, adding a lateral offset to the lateral trajectory planning, and dynamically correcting the lateral offset according to the current curb width and highway grade includes: Determining the initial value of the offset; Determining a first correction coefficient according to the curb width of the current road; determining a second correction coefficient according to the steering curvature of the current own vehicle; Correcting the lateral offset based on the first correction coefficient and the second correction coefficient; The calculation formula of the lateral offset is: ， Where d is the lateral offset, and d0 is the corresponding value when no correction is added to the offset; The offset correction coefficient k is: When the curb width dy is 0, it means that the risk of the driver hitting the road boundary when driving in the outermost lane is very high, and the offset correction coefficient k takes the maximum value of 1; when the curb width dy is 1, it means that the risk of the driver hitting the road boundary when driving in the outermost lane is very small. In order to ensure the lane centering performance, the lateral trajectory is not offset at this time, and the offset correction coefficient k takes the minimum value of 0; when the curb width dy takes a value between 0 and 1, the k value can be calibrated in combination with the actual experience of the driver and passengers. The trend is that as the curb width dy increases, the k value should gradually decrease; The offset correction coefficient γ is: When the curvature ρ is 0, it means that the road is a straight road at this time, and the offset correction coefficient γ does not need to be amplified and takes a value of 1; as the ρ value increases, the bend becomes sharper. At this time, the risk of the driver hitting the road boundary when driving in the outermost lane increases, and the offset correction coefficient γ value needs to be appropriately amplified. Specifically, it needs to be calibrated in combination with the actual experience of the driver and passengers.

2. The lane centering implementation method according to claim 1, wherein The step of determining the first correction coefficient according to the curb width of the current road includes: Establishing a first mapping table between the first correction coefficient and the curb width; Determining the width of the road shoulder according to the grade of the highway; Based on the grade of the highway and the first mapping table, determining the first correction coefficient.

3. The lane centering implementation method according to claim 2, characterized in that, The value of the first correction coefficient is in the interval (0, 1], and the curb width value is in the range of 0.25m to 0.75m.

4. The lane centering implementation method according to claim 1, wherein The step of determining the second correction coefficient according to the steering curvature of the current own vehicle includes: Establishing a second mapping table between the second correction coefficient and the steering curvature; Calculating the steering curvature of the current own vehicle, and matching it with the second mapping table to determine the second correction coefficient.

5. The lane centering implementation method according to any one of claims 1 to 4, wherein the planning of the lateral trajectory of the own vehicle based on the lane lines and lane boundaries is realized by the following method: ， Among them, x and y respectively represent the vertical and horizontal coordinates of the own vehicle in the vehicle coordinate system of the own vehicle, represents the lateral position at the origin of the vehicle coordinate system of the vehicle, , and are all preset trajectory coefficients.

6. A lane centering implementation device, characterized in that, Including: An identification module, configured to identify the lane lines and lane boundaries of the road where the own vehicle is located during driving, and plan the lateral trajectory of the own vehicle based on the lane lines and lane boundaries; A correction module, configured to add a lateral offset to the lateral trajectory planning based on the pose information of its own vehicle, and dynamically correct the lateral offset according to the current curb width and road grade; A centering module, configured to re-plan the lateral trajectory of its own vehicle according to the corrected lateral offset, and center the vehicle in the lane according to the lateral trajectory; The correction module includes: A determination unit, configured to determine an initial value of the offset; A first correction unit, configured to determine a first correction coefficient according to the current curb width of the road; and determine a second correction coefficient according to the current steering curvature of its own vehicle; A second correction unit, configured to correct the lateral offset based on the first correction coefficient and the second correction coefficient; The calculation formula of the lateral offset is: ， where d is the lateral offset, and d0 is the corresponding value when no correction is applied to the offset; The offset correction coefficient k is: When the curb width dy is 0, it indicates that the risk of collision with the road boundary is very high when the driver is driving in the outermost lane, and the offset correction coefficient k takes the maximum value of 1; when the curb width dy is 1, it indicates that the risk of collision with the road boundary is very low when the driver is driving in the outermost lane. To ensure the lane centering performance, the lateral trajectory is not offset at this time, and the offset correction coefficient k takes the minimum value of 0; when the curb width dy ranges from 0 to 1, the k value can be calibrated in combination with the actual experience of the driver and passengers. The trend is that as the curb width dy increases, the k value should gradually decrease; The offset correction coefficient γ is: When the curvature ρ is 0, it indicates that the road is straight at this time, and the offset correction coefficient γ does not need to be amplified and takes the value of 1; as the ρ value increases, the curve becomes sharper. At this time, the risk of collision with the road boundary increases when the driver is driving in the outermost lane, and the offset correction coefficient γ value needs to be appropriately amplified. Specifically, it needs to be calibrated in combination with the actual experience of the driver and passengers.

7. An electronic device, characterized in that, including: One or more processors; A storage device, configured to store one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the lane centering implementation method according to any one of claims 1 to 5.

8. A storage medium, on which a computer program is stored, characterized in that, wherein, The computer program, when executed by a processor, implements the lane centering implementation method according to any one of claims 1 to 5.

Images