A lane selection method, an electronic device, and a computer-readable storage medium

Abstract

This application discloses a lane selection method, electronic device, and computer-readable storage medium, relating to the field of intelligent driving technology. The method involves acquiring the real-time smoothness score of the current lane while meeting safety and navigation requirements, and estimating the smoothness score of candidate lanes using observations of the movement of the preceding vehicle, historical data, or visual texture information. By comparing the differences between the two scores and based on a preset smoothness difference threshold, a decision is made on whether to switch lanes to a candidate lane with better smoothness. This invention solves the technical problems of related intelligent driving systems being unable to perceive smoothness differences between multiple lanes in the same direction and being unable to actively avoid bumpy lanes by introducing a cross-lane smoothness comparison perception and multi-source confidence weighted fusion mechanism. It achieves the technical effects of automatically selecting smooth lanes, improving driving comfort, reducing abnormal wear of vehicle suspension and tires, and suppressing ineffective lane changes under the premise of safety and compliance.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a lane selection method, electronic device, and computer-readable storage medium. Background Technology

[0002] Currently, in actual road environments, especially on urban expressways and elevated sections, there are often significant differences in smoothness between multiple lanes traveling in the same direction. For example, the leftmost lane, due to its proximity to the crash barrier or median strip, has expansion joints that bulge due to aging, forming longitudinal bulges; the rightmost lane, due to the long-term crushing by heavy trucks, has wavy wear or ruts. Currently, intelligent driving systems lack the perception dimension of road surface smoothness, and in the above scenarios, they will stubbornly drive on bumpy lanes, and even if the adjacent lanes are flat and smooth, the system will not actively initiate a lane change. This technical defect leads to the following typical problems: (1) Poor driving comfort: The vehicle continuously drives on bumpy roads, causing significant head shaking for passengers and increasing dizziness; at the same time, the steering wheel vibrates violently, affecting the driving feel. (2) Low user trust: The system's stubborn driving behavior on bumpy lanes appears unintelligent, and users usually evaluate the system as "stupid," and therefore frequently take over manually to avoid bad road conditions, resulting in a significant decrease in the usage rate of intelligent driving systems. (3) Increased vehicle wear and tear: Long-term driving on rough roads will accelerate the abnormal wear and tear of the suspension system, tires and steering mechanism, which will increase the user's after-sales maintenance costs. Summary of the Invention

[0003] This application provides a lane selection method, an electronic device, and a computer-readable storage medium to at least solve the problems in the related art where intelligent driving systems cannot perceive the differences in smoothness between multiple lanes in the same direction and cannot actively avoid bumpy lanes in straight driving scenarios, resulting in poor driving comfort.

[0004] This application provides a lane selection method, which includes: determining candidate lanes, wherein the candidate lanes are adjacent lanes in the same direction as the current lane, and changing lanes from the current lane to the candidate lane meets preset safety and navigation conditions; acquiring first real-time smoothness data corresponding to the current lane, and determining a first smoothness score corresponding to the current lane based on the first real-time smoothness data; acquiring road surface smoothness information corresponding to the candidate lane, and determining a second smoothness score corresponding to the candidate lane based on the road surface smoothness information; comparing the first smoothness score with the second smoothness score; in response to all second smoothness scores being less than or equal to the first smoothness score, determining the current lane as the target lane, and controlling the current vehicle to travel in the current lane; in response to at least one second smoothness score being greater than the first smoothness score, determining the target lane based on at least one second smoothness score, the first smoothness score, and a preset smoothness difference threshold, and controlling the current vehicle to travel in the target lane.

[0005] This application also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program to implement at least the following steps: determining a candidate lane, wherein the candidate lane is an adjacent lane in the same direction as the current lane, and changing lanes from the current lane to the candidate lane satisfies preset safety and navigation conditions; acquiring first real-time smoothness data corresponding to the current lane, and determining a first smoothness score corresponding to the current lane based on the first real-time smoothness data; acquiring road surface smoothness information corresponding to the candidate lane, and determining a second smoothness score corresponding to the candidate lane based on the road surface smoothness information; comparing the first smoothness score with the second smoothness score; in response to all second smoothness scores being less than or equal to the first smoothness score, determining the current lane as the target lane, and controlling the current vehicle to travel in the current lane; in response to at least one second smoothness score being greater than the first smoothness score, determining the target lane based on at least one second smoothness score, the first smoothness score, and a preset smoothness difference threshold, and controlling the current vehicle to travel in the target lane.

[0006] This application also provides a computer-readable storage medium storing a computer program, wherein when executed by a processor, the computer program implements at least the following steps: determining a candidate lane, wherein the candidate lane is an adjacent lane in the same direction as the current lane, and changing lanes from the current lane to the candidate lane satisfies preset safety and navigation conditions; acquiring first real-time smoothness data corresponding to the current lane, and determining a first smoothness score corresponding to the current lane based on the first real-time smoothness data; acquiring road surface smoothness information corresponding to the candidate lane, and determining a second smoothness score corresponding to the candidate lane based on the road surface smoothness information; comparing the first smoothness score with the second smoothness score; in response to all second smoothness scores being less than or equal to the first smoothness score, determining the current lane as the target lane, and controlling the current vehicle to travel in the current lane; in response to at least one second smoothness score being greater than the first smoothness score, determining the target lane based on at least one second smoothness score, the first smoothness score, and a preset smoothness difference threshold, and controlling the current vehicle to travel in the target lane.

[0007] This application, under the premise of meeting safety and navigation conditions, obtains the real-time smoothness score of the current lane and estimates the smoothness score of candidate lanes using observations of the movement of the vehicle ahead, historical data, or visual texture information. By comparing the difference between the two scores and based on a preset smoothness difference threshold, it decides whether to switch lanes to the candidate lane with better smoothness. This invention solves the technical problems of related intelligent driving systems being unable to perceive the smoothness differences of multiple lanes in the same direction and being unable to actively avoid bumpy lanes by introducing a cross-lane smoothness comparison perception and multi-source confidence weighted fusion mechanism. It achieves the technical effects of automatically selecting smooth lanes, improving driving comfort, reducing abnormal wear of vehicle suspension and tires, and suppressing ineffective lane changes under the premise of safety and compliance. Attached Figure Description

[0008] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a flowchart illustrating the lane selection method in the first embodiment; Figure 2 This is a diagram of the internal structure of the electronic device in the second embodiment. Detailed Implementation

[0010] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0011] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0012] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0013] In the first embodiment, such as Figure 1As shown, a lane selection method is provided, comprising: determining candidate lanes, wherein the candidate lanes are adjacent lanes in the same direction as the current lane, and changing lanes from the current lane to the candidate lane meets preset safety and navigation conditions; acquiring first real-time smoothness data corresponding to the current lane, and determining a first smoothness score corresponding to the current lane based on the first real-time smoothness data; acquiring road surface smoothness information corresponding to the candidate lane, and determining a second smoothness score corresponding to the candidate lane based on the road surface smoothness information; comparing the first smoothness score and the second smoothness score; in response to all second smoothness scores being less than or equal to the first smoothness score, determining the current lane as the target lane, and controlling the current vehicle to drive in the current lane; in response to at least one second smoothness score being greater than the first smoothness score, determining the target lane based on at least one second smoothness score, the first smoothness score, and a preset smoothness difference threshold, and controlling the current vehicle to drive in the target lane.

[0014] Specifically, the above method realizes lane selection decision based on smoothness comparison. By acquiring the real-time smoothness of the current lane and the road surface information of the candidate lanes, and comparing the scores of the two, a lane change is triggered when the smoothness of the candidate lane is significantly better than that of the current lane; otherwise, the original lane is maintained. This enables the vehicle to have the ability to "change lanes for smoothness," filling the gap in existing intelligent driving systems in multi-lane smoothness perception and active avoidance of bumpy lanes, and significantly improving driving comfort and system intelligence.

[0015] Further, determining candidate lanes includes: determining whether the lane line type between the current lane and the adjacent lane is a lane-changing permitted type, and determining the adjacent lane with a lane-changing permitted type as the first candidate lane; determining whether there is a collision risk when changing lanes from the current lane to the first candidate lane, and determining the first candidate lane without a collision risk as the second candidate lane; determining whether there are any vehicles traveling in the second candidate lane within the current vehicle's preset perception area, and determining the second candidate lane without any vehicles traveling as the third candidate lane, wherein the perception area is the side and rear area outside the current vehicle's rearview mirror field of view, and the traveling vehicles are vehicles not included in the collision risk assessment by the current vehicle.

[0016] Specifically, the above method ensures the safety foundation of the lane selection process by screening adjacent lanes that allow lane changes, have no collision risk, and have no vehicles in the blind spot. By strictly constraining the smoothness selection within the safe and feasible domain, it avoids introducing collision or blind spot risks in pursuit of smoothness, and realizes the decision-making logic of "safety first, smoothness selection".

[0017] In a specific embodiment, the permitted lane change type refers to whether a vehicle can change lanes from its current lane to an adjacent lane based on traffic rules and lane line types. Specifically, if the lane line between the current lane and the adjacent lane is a dashed line, or a combination of dashed and solid lines where lane changing is permitted on one side of the dashed line, it is determined to be a permitted lane change type; if it is a solid line, or a combination of dashed and solid lines where lane changing is prohibited on one side of the solid line, it is determined to be a prohibited lane change type. Collision risk refers to the possibility of collision between the current vehicle and other vehicles in the target lane (including vehicles approaching from behind, parallel vehicles, or vehicles decelerating in front) during the current vehicle's lane change process. The collision risk assessment is based on relative distance, relative speed, acceleration, and predicted trajectory. If there is a possibility of collision or the safe distance is insufficient, a collision risk is determined to exist. Perception area refers to the area to the side and rear of the current vehicle outside the rearview mirror's field of vision. Vehicles traveling in this area may enter the blind spot when the current vehicle changes lanes and are not completely covered by the sensors (such as forward-looking, side-looking, and rear-looking radars or cameras) used in the collision risk assessment in the conventional lane change safety model.

[0018] Furthermore, determining the candidate lane also includes: obtaining the current position of the current vehicle and determining whether the distance between the current position and the exit position indicated by the current vehicle's navigation system is less than or equal to a preset distance threshold; in response to the distance between the current position and the exit position being greater than the distance threshold, determining the third candidate lane as a candidate lane.

[0019] Specifically, the above method further combines navigation information to determine whether the current vehicle is close to the exit location. Only when the vehicle is far enough away from the exit will the lane that has been safely screened be included in the candidate lane. This is to avoid unnecessary lane changes caused by unevenness factors when approaching the exit, to ensure the feasibility of the navigation path, and to improve the rationality of the system's behavior in highway or expressway scenarios.

[0020] In a specific embodiment, the exit location refers to the predetermined exit point indicated by the vehicle's navigation system for leaving the current road. Exit locations include, but are not limited to: highway ramp exits, expressway auxiliary road exits, elevated bridge downhill ramps, intersection turning points, or the end point of lane guide lines.

[0021] Furthermore, the lane selection method also includes: in response to the fact that changing lanes from the current lane to an adjacent lane does not meet safety conditions and / or navigation conditions, determining the current lane as the target lane and controlling the current vehicle to drive in the current lane; in response to the fact that the distance between the current position and the exit position is less than or equal to a distance threshold, determining the current lane as the target lane.

[0022] Specifically, the above method clarifies that when safety or navigation conditions are not met, the system directly selects the current lane as the target lane to ensure that the vehicle will not violate safety or navigation constraints due to smoothness factors under any circumstances, thereby enhancing the robustness and interpretability of the system.

[0023] Further, the system acquires the first real-time smoothness data corresponding to the current lane, and determines the first smoothness score corresponding to the current lane based on the first real-time smoothness data. This includes: acquiring the first bounce amplitude, first impact frequency, vertical acceleration, longitudinal acceleration, and yaw rate of the current vehicle in the current lane; determining the acceleration / deceleration compensation coefficient based on the longitudinal acceleration, and compensating for acceleration / deceleration interference on the vertical acceleration based on the acceleration / deceleration compensation coefficient to obtain a first target acceleration; determining the steering compensation coefficient based on the yaw rate, and compensating for steering interference on the first target acceleration based on the steering compensation coefficient to obtain a second target acceleration; and determining the first smoothness score corresponding to the current lane based on the first bounce amplitude, first impact frequency, and second target acceleration.

[0024] Specifically, the above method describes in detail the current calculation method of lane smoothness score. By introducing acceleration / deceleration compensation coefficient and steering compensation coefficient to double correct vertical acceleration, driving behavior interference is eliminated, the authenticity and accuracy of smoothness measurement are improved, and the system can reliably distinguish between road bumps and the impact caused by the vehicle's own movement.

[0025] In a specific embodiment, the bounce amplitude and impact frequency are obtained through suspension displacement sensors installed at each wheel suspension system. These sensors collect real-time data on the displacement changes of the suspension relative to the vehicle body. The peak-to-peak value of the displacement signal within a preset time window is extracted as the bounce amplitude, and the number of times the displacement change rate exceeds a preset threshold is counted as the impact frequency. Vertical acceleration, longitudinal acceleration, and yaw rate are obtained through an inertial measurement unit (IMU) located at the vehicle's center of gravity. The IMU includes a three-axis accelerometer and a three-axis gyroscope. Vertical acceleration is obtained from the Z-axis output of the accelerometer after low-pass filtering; longitudinal acceleration is obtained from the X-axis output of the accelerometer after gravity component removal; and yaw rate is obtained from the Z-axis output of the gyroscope after low-pass filtering and zero-bias correction. Vertical acceleration is further compensated for interference based on longitudinal acceleration and yaw rate to eliminate the influence of pitch motion caused by acceleration / deceleration and roll motion caused by steering on the vertical acceleration measurement.

[0026] Further, based on the first bounce amplitude, the first impact frequency, and the second target acceleration, the first smoothness score corresponding to the current lane is determined, including: determining the first amplitude feature value, the first frequency feature value, and the vertical vibration feature value corresponding to the current lane based on the first bounce amplitude, the first impact frequency, and the second target acceleration, respectively; determining the first amplitude weighting coefficient corresponding to the first amplitude feature value, the first frequency weighting coefficient corresponding to the first frequency feature value, and the vertical weighting coefficient corresponding to the vertical vibration feature value; and weighting and fusing the first amplitude feature value, the first frequency feature value, and the vertical vibration feature value based on the first amplitude weighting coefficient, the first frequency weighting coefficient, and the vertical weighting coefficient to obtain the first smoothness score corresponding to the current lane.

[0027] Specifically, the above method extracts feature values ​​from the current lane's bounce amplitude, impact frequency, and corrected vertical acceleration, and assigns different weights to perform weighted fusion to comprehensively reflect the intensity, frequency, and vertical vibration characteristics of road surface bumps, generating a multi-dimensional smoothness score and improving the ability to identify different bump patterns.

[0028] Further, the process involves acquiring road surface smoothness information corresponding to candidate lanes, and determining a second smoothness score for each candidate lane based on the road surface smoothness information. This includes: acquiring at least one of real-time smoothness data, historical smoothness data, and visual texture data corresponding to candidate lanes; determining at least one of a first confidence level corresponding to the real-time smoothness data, a second confidence level corresponding to the historical smoothness data, and a third confidence level corresponding to the visual texture data; determining a real-time smoothness score for each candidate lane based on the first confidence level and the real-time smoothness data, and / or determining a historical smoothness score for each candidate lane based on the second confidence level and the historical smoothness data, and / or determining a visual smoothness score for each candidate lane based on the third confidence level and the visual texture data; and determining a second smoothness score for each candidate lane based on at least one of the real-time smoothness score, the historical smoothness score, and the visual smoothness score.

[0029] Specifically, the above method provides three complementary information sources for candidate lane smoothness estimation: second real-time smoothness data, historical smoothness data, and visual texture data, and allows fusion based on confidence level. It solves the core problem of "not being able to perceive smoothness before entering the lane" and can obtain candidate lane smoothness estimation even under different perception conditions (such as no preceding vehicle / no history / poor lighting), thus improving the system's environmental adaptability and information completeness.

[0030] In a specific embodiment, the second real-time smoothness data includes at least the second bounce amplitude and the second impact frequency corresponding to the vehicle in front of the current vehicle in the candidate lane, the historical smoothness data includes at least the smoothness information corresponding to the candidate lane in the local cache, and the visual texture data includes at least the road surface patch information, road surface crack information, and road surface manhole cover information of the candidate lane.

[0031] In a specific embodiment, "vehicles ahead" refers to other motor vehicles located in the candidate lane ahead of the current vehicle's direction of travel. Vehicles ahead include, but are not limited to, one or more vehicles within the candidate lane that can be stably tracked by the current vehicle's perception system (such as cameras, millimeter-wave radar, or lidar). In the context of smoothness estimation, "vehicles ahead" specifically refers to reference vehicles within the candidate lane used to observe vertical sway behavior. First confidence level: a quantitative value indicating the degree of confidence in the real-time smoothness data of the candidate lane obtained by the "vehicle motion observation method".

[0032] The first confidence level is determined based on, but is not limited to, the type of the vehicle ahead (e.g., sedan, SUV, truck), suspension status (e.g., whether it has active suspension or air suspension), driving stability (e.g., whether there are abnormal behaviors such as swerving, sudden acceleration or deceleration), and the duration and quality of the current vehicle's perception of the vehicle ahead. A higher first confidence level indicates that the movement of the vehicle ahead more accurately reflects the road surface smoothness of the candidate lane; conversely, if the vehicle ahead has strong damping performance or abnormal driving behavior, the first confidence level is lowered, weakening its contribution to the smoothness estimation.

[0033] Second confidence level: This refers to the quantified value of the reliability of the historical smoothness data of candidate lanes obtained by the "historical trajectory rewriting method". The value of the second confidence level is based on, but is not limited to: the collection time of the historical smoothness data (the more recent the data, the higher the confidence level), the number of data sources (the more vehicles involved in the collection, the higher the confidence level), and data consistency (the degree of difference between multiple collection results; the smaller the difference, the higher the confidence level). A higher second confidence level indicates that the historical data has greater reference value for the smoothness of candidate lanes at the current moment; conversely, if the data is outdated, comes from a single source, or the results of multiple collections are contradictory, the second confidence level should be reduced to avoid relying on unreliable historical information.

[0034] Third confidence level: This refers to the quantified value of the credibility of the visual texture smoothness data of candidate lanes obtained by the "visual texture recognition method". The value of the third confidence level is determined based on factors including, but not limited to, the image quality of the visual texture data (resolution, sharpness, noise level), lighting conditions (such as daytime, dusk, nighttime, backlighting), and the degree of road surface occlusion (such as the degree to which it is covered by vehicles ahead, water stains, snow, or fallen leaves). A higher third confidence level indicates that the features such as road surface patches, cracks, and manhole cover density identified by visual recognition can more accurately reflect the smoothness of the candidate lane; conversely, in cases of blurred images, poor lighting, or severe road surface occlusion, the third confidence level should be reduced to avoid visual misjudgment.

[0035] Confidence fusion principle: The first, second, and third confidence levels are used to weight and correct the smoothness estimation results obtained by the "previous vehicle motion observation method," "historical trajectory rewriting method," and "visual texture recognition method," respectively. When the confidence level of a certain perception source is lower than the preset confidence threshold, the system reduces or discards the contribution of that source to the candidate lane smoothness score, and other high-confidence sources dominate the estimation results, thereby achieving robust smoothness estimation with multi-source complementarity and no dependence on a single perception source.

[0036] Further, determining the first confidence level corresponding to the second real-time smoothness data includes: obtaining reference feature information of the vehicle ahead in the candidate lane, wherein the reference feature information includes at least one of the vehicle type information, suspension state information, and driving stability information; determining the first confidence level corresponding to the second real-time smoothness data based on the reference feature information; and determining the real-time smoothness score corresponding to the candidate lane based on the first confidence level and the second real-time smoothness data, including: weighting and correcting the second real-time smoothness data based on the first confidence level to obtain the real-time smoothness score corresponding to the candidate lane.

[0037] Specifically, when using the forward vehicle movement observation method, the above method performs confidence-weighted correction on the second real-time smoothness data based on information such as the type of the forward vehicle, suspension status, and driving stability. This avoids misjudging the smoothness of the candidate lane due to the forward vehicle's strong shock absorption or abnormal driving, thus improving the reliability and accuracy of the observation method.

[0038] Further, determining the first confidence level corresponding to the second real-time smoothness data includes: obtaining reference feature information of the vehicle ahead in the candidate lane, wherein the reference feature information includes at least one of the vehicle type information, suspension state information, and driving stability information; determining the first confidence level corresponding to the second real-time smoothness data based on the reference feature information; and determining the real-time smoothness score corresponding to the candidate lane based on the first confidence level and the second real-time smoothness data, including: weighting and correcting the second real-time smoothness data based on the first confidence level to obtain the real-time smoothness score corresponding to the candidate lane.

[0039] Specifically, when utilizing historical flatness data, the above method performs confidence assessment and weighted correction based on information such as data collection time, number of sources, and consistency to ensure the validity of historical data and avoid misleading decisions using outdated or low-quality data. At the same time, it supports data closure in crowdsourcing collaboration scenarios, enabling "learn once, reuse throughout the vehicle".

[0040] Further, determining the third confidence level corresponding to the visual texture data includes: acquiring the acquisition environment information of the visual texture data, wherein the acquisition environment information includes at least one of the image quality information, lighting condition information, and road surface occlusion information of the visual texture data; determining the third confidence level corresponding to the visual texture data based on the acquisition environment information; and determining the visual smoothness score corresponding to the candidate lane based on the third confidence level and the visual texture data, including: performing weighted correction on the visual texture data based on the third confidence level to obtain the visual smoothness score corresponding to the candidate lane.

[0041] Specifically, when using visual texture recognition, the above method performs confidence-weighted correction on visual smoothness data based on information such as image quality, lighting conditions, and road surface occlusion, which improves the robustness of visual perception in complex environments, avoids erroneous smoothness estimation caused by poor lighting or road surface occlusion, and enhances the system's all-weather adaptability.

[0042] Further, based on at least one second smoothness score, a first smoothness score, and a preset smoothness difference threshold, a target lane is determined, and the current vehicle is controlled to travel in the target lane, including: calculating the smoothness difference between at least one second smoothness score and the first smoothness score; comparing the smoothness difference with the smoothness difference threshold; in response to all smoothness differences being less than the smoothness difference threshold, determining the current lane as the target lane, and controlling the current vehicle to travel in the current lane; in response to at least one smoothness difference being greater than or equal to the smoothness difference threshold, determining the candidate lane with the largest second smoothness score as the target lane, and controlling the current vehicle to travel in the target lane.

[0043] Specifically, the above method calculates the smoothness difference between the candidate lane and the current lane and compares it with a preset smoothness difference threshold. It selects the optimal candidate lane only when the smoothness difference is significant; otherwise, it maintains the current lane. By introducing an "ineffective lane change suppression" mechanism, this method avoids frequent left and right lane changes caused by minor smoothness differences, thus improving the consistency of driving behavior and user acceptance.

[0044] In a specific embodiment, when both candidate lane A and candidate lane B meet the above conditions and the difference in their smoothness scores is within a preset threshold, the optimal target lane can be determined by combining traffic efficiency.

[0045] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0046] In a second embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it performs the following steps: determining a candidate lane, wherein the candidate lane is an adjacent lane in the same direction as the current lane, and changing lanes from the current lane to the candidate lane meets preset safety and navigation conditions; acquiring first real-time smoothness data corresponding to the current lane, and determining a first smoothness score corresponding to the current lane based on the first real-time smoothness data; acquiring road surface smoothness information corresponding to the candidate lane, and determining a second smoothness score corresponding to the candidate lane based on the road surface smoothness information; comparing the first smoothness score with the second smoothness score; in response to all second smoothness scores being less than or equal to the first smoothness score, determining the current lane as the target lane, and controlling the current vehicle to travel in the current lane; in response to at least one second smoothness score being greater than the first smoothness score, determining the target lane based on at least one second smoothness score, the first smoothness score, and a preset smoothness difference threshold, and controlling the current vehicle to travel in the target lane.

[0047] When the program instructions are read and executed by one or more processors, they can also perform operations corresponding to the steps in the above method embodiments, as described above, and will not be repeated here. Reference Figure 2 This example illustrates the architecture of an electronic device, which may include a processor 210, a video display adapter 211, a disk drive 212, an input / output interface 213, a network interface 214, and a memory 220. The processor 210, video display adapter 211, disk drive 212, input / output interface 213, network interface 214, and memory 220 can communicate with each other via a communication bus 230.

[0048] The processor 210 can be implemented using a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided in this application.

[0049] The memory 220 can be implemented as a read-only memory (ROM), random access memory (RAM), static storage device, dynamic storage device, etc. The memory 220 can store the operating system 221 for controlling the operation of the electronic device 200, and the basic input / output system (BIOS) 222 for controlling the low-level operations of the electronic device 200. Additionally, it can store a web browser 223, data storage management 224, and an icon / font processing system 225. The icon / font processing system 225 can be the application program that specifically implements the aforementioned steps in this embodiment. In summary, when implementing the technical solution provided in this application through software or firmware, the relevant program code is stored in the memory 220 and executed by the processor 210.

[0050] Input / output interface 213 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0051] Network interface 214 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0052] Bus 230 includes a pathway for transmitting information between various components of the device, such as processor 210, video display adapter 211, disk drive 212, input / output interface 213, network interface 214, and memory 220.

[0053] In addition, the electronic device 200 can also obtain information on specific acquisition conditions from a virtual resource object acquisition condition information database (not shown in the figure) for condition judgment.

[0054] It should be noted that although the above-described electronic device 200 only shows a processor 210, a video display adapter 211, a disk drive 212, an input / output interface 213, a network interface 214, a memory 220, and a bus 230, in specific implementations, the electronic device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the solution of this application, and does not necessarily include all the components shown in the figures.

[0055] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause an electronic device (which may be a personal computer, cloud server, or network device, etc.) to execute the methods of various embodiments or some parts of the embodiments of this application.

[0056] In a third embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it performs the following steps: determining a candidate lane, wherein the candidate lane is an adjacent lane in the same direction as the current lane, and changing lanes from the current lane to the candidate lane meets preset safety and navigation conditions; acquiring first real-time smoothness data corresponding to the current lane, and determining a first smoothness score corresponding to the current lane based on the first real-time smoothness data; acquiring road surface smoothness information corresponding to the candidate lane, and determining a second smoothness score corresponding to the candidate lane based on the road surface smoothness information; comparing the first smoothness score with the second smoothness score; in response to all second smoothness scores being less than or equal to the first smoothness score, determining the current lane as the target lane, and controlling the current vehicle to travel in the current lane; in response to at least one second smoothness score being greater than the first smoothness score, determining the target lane based on at least one second smoothness score, the first smoothness score, and a preset smoothness difference threshold, and controlling the current vehicle to travel in the target lane.

[0057] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0058] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0059] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application.

[0060] In a fourth embodiment, a computer program product is provided, on which a computer program is stored. When the computer program is executed by a processor, it performs the following steps: determining a candidate lane, wherein the candidate lane is an adjacent lane in the same direction as the current lane, and changing lanes from the current lane to the candidate lane meets preset safety and navigation conditions; acquiring first real-time smoothness data corresponding to the current lane, and determining a first smoothness score corresponding to the current lane based on the first real-time smoothness data; acquiring road surface smoothness information corresponding to the candidate lane, and determining a second smoothness score corresponding to the candidate lane based on the road surface smoothness information; comparing the first smoothness score with the second smoothness score; in response to all second smoothness scores being less than or equal to the first smoothness score, determining the current lane as the target lane, and controlling the current vehicle to travel in the current lane; in response to at least one second smoothness score being greater than the first smoothness score, determining the target lane based on at least one second smoothness score, the first smoothness score, and a preset smoothness difference threshold, and controlling the current vehicle to travel in the target lane.

[0061] In a fourth embodiment, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it performs the following steps: determining a candidate lane, wherein the candidate lane is an adjacent lane in the same direction as the current lane, and changing lanes from the current lane to the candidate lane meets preset safety and navigation conditions; acquiring first real-time smoothness data corresponding to the current lane, and determining a first smoothness score corresponding to the current lane based on the first real-time smoothness data; acquiring road surface smoothness information corresponding to the candidate lane, and determining a second smoothness score corresponding to the candidate lane based on the road surface smoothness information; comparing the first smoothness score with the second smoothness score; in response to all second smoothness scores being less than or equal to the first smoothness score, determining the current lane as the target lane, and controlling the current vehicle to travel in the current lane; in response to at least one second smoothness score being greater than the first smoothness score, determining the target lane based on at least one second smoothness score, the first smoothness score, and a preset smoothness difference threshold, and controlling the current vehicle to travel in the target lane.

[0062] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer program product, and when the computer program is executed, it can include the processes of the embodiments of the methods described above.

[0063] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0064] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application.

Claims

1. A lane selection method, characterized in that, The method includes: Determine candidate lanes, wherein the candidate lanes are adjacent lanes traveling in the same direction as the current lane, and changing lanes from the current lane to the candidate lanes meets preset safety and navigation conditions; Obtain the first real-time smoothness data corresponding to the current lane, and determine the first smoothness score corresponding to the current lane based on the first real-time smoothness data; Obtain the road surface smoothness information corresponding to the candidate lane, and determine the second smoothness score corresponding to the candidate lane based on the road surface smoothness information; Compare the first flatness score with the second flatness score; In response to the fact that the second smoothness score is less than or equal to the first smoothness score, the current lane is determined as the target lane, and the current vehicle is controlled to travel in the current lane; In response to at least one second smoothness score being greater than the first smoothness score, the target lane is determined based on the at least one second smoothness score, the first smoothness score, and a preset smoothness difference threshold, and the current vehicle is controlled to travel in the target lane.

2. The method according to claim 1, characterized in that, The step of obtaining the first real-time smoothness data corresponding to the current lane and determining the first smoothness score corresponding to the current lane based on the first real-time smoothness data includes: The first bounce amplitude, first impact frequency, vertical acceleration, longitudinal acceleration, and yaw rate of the current vehicle in the current lane are obtained. The acceleration / deceleration compensation coefficient is determined based on the longitudinal acceleration, and the vertical acceleration is compensated for acceleration / deceleration interference based on the acceleration / deceleration compensation coefficient to obtain the first target acceleration; The steering compensation coefficient is determined based on the yaw rate, and the steering interference is compensated for the first target acceleration based on the steering compensation coefficient to obtain the second target acceleration; The first smoothness score corresponding to the current lane is determined based on the first bounce amplitude, the first impact frequency, and the second target acceleration.

3. The method according to claim 2, characterized in that, The step of determining the first smoothness score corresponding to the current lane based on the first bounce amplitude, the first impact frequency, and the second target acceleration includes: Based on the first jump amplitude, the first impact frequency, and the second target acceleration, the first amplitude characteristic value, the first frequency characteristic value, and the vertical vibration characteristic value corresponding to the current lane are determined respectively. Determine the first amplitude weighting coefficient corresponding to the first amplitude feature value, the first frequency weighting coefficient corresponding to the first frequency feature value, and the vertical weighting coefficient corresponding to the vertical vibration feature value; Based on the first amplitude weighting coefficient, the first frequency weighting coefficient, and the vertical weighting coefficient, the first amplitude feature value, the first frequency feature value, and the vertical vibration feature value are weighted and fused to obtain the first smoothness score corresponding to the current lane.

4. The method according to claim 1, characterized in that, The step of obtaining the road surface smoothness information corresponding to the candidate lane and determining the second smoothness score corresponding to the candidate lane based on the road surface smoothness information includes: Obtain at least one of the following data: second real-time smoothness data, historical smoothness data, and visual texture data corresponding to the candidate lane; Determine at least one of the following confidence levels: the first confidence level corresponding to the second real-time flatness data, the second confidence level corresponding to the historical flatness data, and the third confidence level corresponding to the visual texture data; Based on the first confidence level and the second real-time smoothness data, determine the real-time smoothness score corresponding to the candidate lane, and / or based on the second confidence level and the historical smoothness data, determine the historical smoothness score corresponding to the candidate lane, and / or based on the third confidence level and the visual texture data, determine the visual smoothness score corresponding to the candidate lane. The second smoothness score corresponding to the candidate lane is determined based on at least one of the real-time smoothness score, the historical smoothness score, and the visual smoothness score.

5. The method according to claim 4, characterized in that, Determining the first confidence level corresponding to the second real-time flatness data includes: Obtain reference feature information of the vehicle ahead in the candidate lane, wherein the reference feature information includes at least one of the vehicle ahead type information, suspension status information and driving stability information; Based on the reference feature information, determine the first confidence level corresponding to the second real-time flatness data; The step of determining the real-time smoothness score corresponding to the candidate lane based on the first confidence level and the second real-time smoothness data includes: The second real-time smoothness data is weighted and corrected based on the first confidence level to obtain the real-time smoothness score corresponding to the candidate lane.

6. The method according to claim 4, characterized in that, Determining the second confidence level corresponding to the historical flatness data includes: Obtain quality assessment information of the historical flatness data, wherein the quality assessment information includes at least one of the following: data collection time information, data source quantity information, and data consistency information; Based on the quality assessment information, determine the second confidence level corresponding to the historical flatness data; The step of determining the historical smoothness score corresponding to the candidate lane based on the second confidence level and the historical smoothness data includes: The historical smoothness data is weighted and corrected based on the second confidence level to obtain the historical smoothness score corresponding to the candidate lane.

7. The method according to claim 4, characterized in that, Determining the third confidence level corresponding to the visual texture data includes: Acquire the acquisition environment information of the visual texture data, wherein the acquisition environment information includes at least one of the image quality information, lighting condition information, and road surface occlusion information of the visual texture data; Based on the collected environmental information, the third confidence level corresponding to the visual texture data is determined; The step of determining the visual smoothness score corresponding to the candidate lane based on the third confidence level and the visual texture data includes: The visual texture data is weighted and corrected based on the third confidence level to obtain the visual smoothness score corresponding to the candidate lane.

8. The method according to claim 1, characterized in that, The step of determining the target lane based on at least one second smoothness score, the first smoothness score, and a preset smoothness difference threshold, and controlling the current vehicle to travel in the target lane, includes: Calculate the flatness difference between the at least one second flatness score and the first flatness score; The flatness difference is compared with the flatness difference threshold. In response to the fact that all the smoothness differences are less than the smoothness difference threshold, the current lane is determined to be the target lane, and the current vehicle is controlled to travel in the current lane; In response to at least one of the smoothness differences being greater than or equal to the smoothness difference threshold, the candidate lane with the largest second smoothness score is determined as the target lane, and the current vehicle is controlled to travel in the target lane.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the lane selection method as described in any one of claims 1 to 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the lane selection method as described in any one of claims 1 to 8.

Images