Lane center line confirmation method and device and medium

Abstract

The invention discloses a lane center line confirmation method for avoiding mistaken direction turning at an intersection in an intelligent navigation mode. According to the confirmation method, firstly, effectiveness and smoothness judgment is carried out on left and right side lane lines respectively, and a quantitative basis is provided for decision making; and then, based on a judgment result, according to a preset decision logic comprising four modes of double-side fitting, left-side single-side fitting, right-side single-side fitting and non-following line control, adaptively selecting a center line fitting mode. According to the technical scheme, the system can effectively screen and utilize reliable lane line information in a complex intersection environment, or give up line following in time when the lane line information is not suitable, so that the problem that a vehicle mistakenly turns the direction due to the fact that sensing information jumps or is wrong is fundamentally solved, and the driving safety of the vehicle is improved. And the transverse control safety and the system robustness during crossing are obviously improved.

Description

Technical Field

[0001] This application relates to the field of Advanced Driving Assistance System (ADAS) technology, and in particular to a lane centerline confirmation method for stabilizing vehicle direction and avoiding accidental steering when passing through intersections in systems with lateral control functions such as Integrated Cruise Assist (ICA). Background Technology

[0002] Intelligent lane-keeping assist systems (ILS) integrate information from sensors such as cameras and radar to identify and track lane lines, enabling lane centering control. However, when approaching intersections, due to the discontinuity, wear, and obstruction of lane lines, as well as the influence of environmental factors such as backlighting, rain, and fog, the lane line information output by the perception system often exhibits sudden changes, sharp drops in confidence, or brief disappearances. This causes drastic changes in the calculated road centerline (i.e., lane centerline), leading to erroneous lateral control commands, manifesting as the vehicle "mistakenly turning the steering wheel," seriously threatening driving safety and significantly impacting the user experience.

[0003] Existing technologies, such as directly disengaging lateral control or switching to follow mode at intersections, suffer from drawbacks such as inconsistent functionality and unstable following trajectories. Therefore, there is an urgent need for a method that can intelligently assess and utilize lane line information in intersection scenarios to ensure smooth and stable lateral control. Summary of the Invention

[0004] The purpose of this application is to overcome the shortcomings of existing technologies and provide a lane centerline confirmation method that can adaptively process complex lane line information at intersections and effectively avoid mis-steering. To achieve the above objective, this application proposes the following technical solution.

[0005] In a first aspect, embodiments of this application provide a method for confirming the lane centerline, including:

[0006] The effectiveness and smoothness of the left and right lane lines are assessed separately.

[0007] Based on the results of the validity and smoothness assessments, a centerline fitting mode is selected according to a preset decision logic; wherein, the decision logic includes:

[0008] When the first condition is met, a two-sided fitting mode is adopted;

[0009] When the second condition is met, the left-side one-sided fitting mode is adopted;

[0010] When the third condition is met, the right-side one-sided fitting mode is adopted;

[0011] If any of the above conditions are not met, the center line is deemed invalid, and the system enters non-following-line control mode.

[0012] Furthermore, the first condition is:

[0013] The right lane line is valid, the left lane line is valid, and the difference in the smoothness index between the two lane lines is less than the first set threshold.

[0014] Furthermore, the second condition includes one or more of the following sub-conditions:

[0015] The right lane line is valid, the left lane line is valid, the difference in the smoothness index of the two lane lines is greater than the first set threshold, and the smoothness of the left lane line is better than the set standard.

[0016] The right lane markings are invalid, while the left lane markings are valid, and the smoothness of the left lane markings is better than the set standard.

[0017] Furthermore, the third condition includes one or more of the following sub-conditions:

[0018] The right lane line is valid, the left lane line is valid, the difference in the smoothness index of the two lane lines is greater than the first set threshold, and the smoothness of the right lane line is better than the set standard.

[0019] The right lane markings are valid, while the left lane markings are invalid, and the smoothness of the right lane markings is better than the set standard.

[0020] Furthermore, in the dual-side fitting mode, the centerline confirmation strategy prioritizes the availability of the right lane line.

[0021] Furthermore, entering the non-follow-the-line control mode includes:

[0022] Determine if there is a vehicle ahead that meets the following conditions; if so, switch to following control mode.

[0023] Furthermore, entering the non-follow-the-line control mode also includes:

[0024] If there is no vehicle ahead that meets the following conditions, the corner holding logic is activated, and the lateral control function does not degrade to pass through the intersection.

[0025] Furthermore, the basis for the validity judgment includes:

[0026] Whether the confidence level of the lane line provided by the sensor is higher than the preset confidence level threshold.

[0027] Furthermore, the smoothness judgment is achieved by calculating the variance of the lateral distance between the lane line and the vehicle's historical trajectory line at multiple preset points. The smaller the variance, the smoother the lane line.

[0028] Furthermore, the smoothness index includes variance weight values, and the formulas for calculating the variance weight values ​​of the left lane line and the right lane line are as follows:

[0029] L vwv =L var / (L var +R var );

[0030] R vwv =R var / (L var +R var );

[0031] Among them, L var R represents the variance between the left lane line and the historical trajectory line. var L represents the variance between the right lane line and the historical trajectory line. vwv R represents the variance weight value of the left lane line; vwv This represents the variance weight value of the right lane line; the variance weight difference V. vw =|L vwv -R vwv The smaller the variance weight difference, the more similar the smoothness of the lane lines on both sides.

[0032] Furthermore, when the lane line data on one side is incomplete, the data is first supplemented based on the complete lane line data on the other side and the standard lane width information, and then the smoothness judgment is made.

[0033] Furthermore, after adopting the single-sided fitting mode, the status of the other lane line is continuously monitored; when the other lane line becomes effective and the difference between the smoothness index of the lane line currently in use and the lane line is less than the first set threshold, the system smoothly switches to the double-sided fitting mode.

[0034] Furthermore, the lane centerline confirmation method is implemented in the lateral control module of the vehicle intelligent navigation assistance system. The lateral control module controls the steering wheel angle of the vehicle in real time based on the lane centerline generated by the selected fitting mode or the command of the non-following control mode.

[0035] Secondly, embodiments of this application provide an electronic device, including: one or more processors;

[0036] A memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors are able to implement the steps in the lane centerline confirmation method described in any of the preceding claims.

[0037] Thirdly, embodiments of this application provide a computer-readable medium storing a computer program, which, when executed by a processor, can implement the steps in the lane centerline confirmation method described in any of the preceding claims.

[0038] This application discloses a lane centerline confirmation method for avoiding mis-steering at intersections in intelligent navigation mode. The method first assesses the effectiveness and smoothness of the left and right lane lines, providing quantitative data for decision-making. Then, based on the assessment results, it adaptively selects the centerline fitting mode according to a preset decision logic that includes four modes: two-sided fitting, left-side single-sided fitting, right-side single-sided fitting, and non-follow-the-line control. Through this technical solution, the system can effectively filter and utilize reliable lane line information in complex intersection environments, or promptly abandon lane following when it is inapplicable. This fundamentally avoids the problem of mis-steering caused by abrupt or erroneous perception information, significantly improving lateral control safety and system robustness when crossing intersections. Attached Figure Description

[0039] Figure 1 This is one of the core flowcharts of a lane centerline confirmation method for avoiding accidental steering at intersections in intelligent navigation mode, provided in an embodiment of this application.

[0040] Figure 2 The second core flowchart of a lane centerline confirmation method for avoiding accidental steering at intersections in intelligent navigation mode provided in this application embodiment;

[0041] Figure 3 A schematic diagram illustrating the process of entering the non-follow-line control mode provided in an embodiment of this application;

[0042] Figure 4 This is a schematic diagram of the module structure of the intelligent navigation assistance system provided in the embodiments of this application;

[0043] Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0044] To enable those skilled in the art to better understand the technical solutions of this application, exemplary embodiments of this application are described below with reference to the accompanying drawings, including various details of the embodiments of this application to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description. Unless otherwise specified, the various embodiments of this application and the features within those embodiments can be combined with each other.

[0045] As used herein, the term "and / or" includes any and all combinations of one or more of the associated enumerated entries. The terminology used herein is for describing particular embodiments only and is not intended to limit the application. As used herein, the singular forms "a" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that when the terms "comprising" and / or "made of" are used herein, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as "connected" or "linked" are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0046] Unless otherwise specified, all terms used in this application (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It should also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this application, and will not be interpreted as having an idealized or overly formal meaning, unless expressly so defined in this application.

[0047] Intelligent Cruise Assist (ICA) provides drivers with longitudinal and lateral assistance functions. Through intelligent driving assistance sensors, it detects traffic targets, lane lines, road edges, and other information to achieve vehicle centering control within the lane, reducing driver workload and improving driving safety and comfort. However, limitations imposed by the environment, lane line quality, and sensor performance prevent complete accuracy in lane information recognition. For example, limited perception in backlight, low light, rain, or fog, or unclear or incorrect road markings, can lead to incorrect lane line information transmission. This is especially common when approaching intersections, where lane line changes are frequently detected abruptly. This results in lateral control deviations, manifesting as mis-steering and an uncomfortable Advanced Driver Assistance Systems (ADAS) user experience, significantly reducing driver trust in the assistance features.

[0048] Existing technology discloses a method to avoid accidental steering, which involves immediately downgrading the ICA (Inter-Car Cruise Assist) function upon intersection detection. This means maintaining longitudinal adaptive cruise control while disabling lateral control, requiring the driver to manually maintain steering wheel control. However, this direct downgrading of the ICA function upon intersection detection leads to frequent downgrading and reactivation on urban roads, resulting in an inconsistent user experience.

[0049] Existing technology two discloses a method that directly enters a following control mode upon detecting an intersection. This means that after detecting an intersection, lateral control is performed based on the lateral position of the vehicle in front in the current lane, rather than on lane lines. However, this approach also has limitations in practical applications. The reason is that the trajectory of the vehicle in front is not stable. To ensure the safety of following control, a threshold with high redundancy is often required to promptly exit the function when the lateral deviation of the vehicle in front is slightly large or fast. Furthermore, the timing for switching to following control when lane lines are detected is difficult to determine.

[0050] In view of this, this application proposes a lane centerline calculation (confirmation) method to avoid accidental steering when approaching intersections in intelligent navigation mode. When approaching an intersection, the road centerline is calculated by comprehensively considering the confidence and smoothness of the identified lane lines on both sides. This avoids centerline jumps caused by inaccurate lane line information, which could lead to inappropriate calculated steering angle requests and interference with the vehicle's lateral control. Overall, this application aims to solve the technical problem of accidental steering when approaching intersections.

[0051] The main objective of this application is to address the problem of inaccurate lane line information leading to mis-steering when approaching an intersection. It proposes a lane centerline calculation method that comprehensively considers lane line confidence and ride comfort. Under the condition of approaching an intersection, the usability and rationality of the identified lane line information on both sides of the lane are comprehensively evaluated, and a reasonable lane centerline is fitted to ensure the stability of lateral control when passing through the intersection.

[0052] To achieve the above objectives, refer to Figure 1 and Figure 2 One embodiment of this application proposes a method for calculating (confirming) the lane centerline to avoid mis-steering when crossing intersections in intelligent navigation mode. This method may specifically include the following steps.

[0053] Step 1: Perform validity and smoothness assessments on the left and right lane lines respectively.

[0054] Specifically, the system assesses the validity and smoothness of lane markings on both sides of the lane. If the confidence level of the identified lane markings exceeds a set threshold, the lane markings are considered valid. For example, the system directly reads the confidence levels of the left and right lane markings output by the sensing module; if these levels exceed a preset threshold (e.g., 0.65), they are considered "valid." This provides a direct and quantifiable standard for determining validity, making it simple and reliable. The sensors output lane marking confidence information, and the system uses this raw confidence information to determine lane marking validity. By directly using sensor data without relying on external corrections, the system improves response speed and independence.

[0055] Lane smoothness is assessed by calculating the variance between the lane line and the historical trajectory line; a smaller variance indicates a smoother lane line. For example, the system selects N preset points along the planned path, calculates the lateral distance from each point to the identified lane line, and then calculates the variance of these N distance values. A smaller variance indicates a smoother lane line. This variance quantifies the local stability of the lane line, which is a key indicator for evaluating its suitability for fine-grained lateral control.

[0056] By calculating the difference in variance weights between the two lane lines, the smaller the difference, the more similar the smoothness of the two lane lines. This difference can intuitively reflect the relative difference in the quality of the two lane lines, eliminate the influence of the absolute value of variance on the judgment, and make the system focus on the "relative credibility" of the two lane lines, making the decision more reasonable.

[0057] More specifically, the variance calculation method is as follows: Take the lane line with the longer longitudinal distance detected by the sensor as the baseline, and complete the other side according to the lane line calculation equation. Select 10 points longitudinally evenly along the vehicle's current position towards the forward trajectory line, and connect them horizontally to the lane lines on both sides, obtaining 10 line segments on each side. Calculate the variance of these 10 line segments on each side, and let L be the variance between the calculated left lane line and the historical trajectory line. var The variance of the right lane line and the historical trajectory line is R. var .

[0058] The method for calculating variance weights is as follows:

[0059] Let the variance weight of the left lane line be L vwv The variance weight of the right lane line is R. vwv Then we have:

[0060] L vwv =L var / (L var +R var ) ;

[0061] R vwv =R var / (L var+R var );

[0062] Let the variance weight difference be V vw Then we have:

[0063] V vw =|L vwv -R vwv |;

[0064] Step 1 proposes a method for evaluating the effectiveness and smoothness of lane lines. The availability of lane lines can be initially assessed through confidence level judgment and variance calculation.

[0065] Step 2: Based on the results of the validity and smoothness judgments, select a centerline fitting mode according to a preset decision logic. The decision logic includes: when the first condition is met, adopt a two-sided fitting mode; when the second condition is met, adopt a left-side one-sided fitting mode; when the third condition is met, adopt a right-side one-sided fitting mode; when none of the above conditions are met, determine that the centerline is invalid and enter a non-following-line control mode. The decision logic specifically includes:

[0066] (a) Prioritize the availability of the right lane line when calculating the lane centerline. For example, in two-sided fitting, the calculated lane centerline may be slightly biased laterally towards the right lane line, or the right lane line data may be given a higher reliability weight within the algorithm. Given the common situation of left-turn waiting areas at intersections in Chinese road environments, this strategy effectively prevents vehicles from mistakenly entering the waiting area, a key detail for improving intersection safety.

[0067] If both the right and left lane lines are valid, and the difference in their variance weights is less than a set threshold, then the lane centerline is fitted based on the two lane lines. For example, if the confidence levels of both lane lines are higher than 0.7, and the calculated difference in variance weights V... vw If the value is less than 0.2, the system fits the lane centerline by taking the midpoint of both lane lines. This clarifies the optimal processing method when both lane lines are of good quality and in consistent condition, ensuring the accuracy of the lane centerline calculation.

[0068] (b) If the right lane line is valid and the left lane line is valid, and the difference in variance weights between the two lane lines is greater than a set threshold, then if the variance L between the left lane line and the historical trajectory line is... var If the value is less than the set threshold, the road centerline is fitted based on the left lane line. For example, both sides are effective, but the variance weight difference is too large (e.g., V). vw =0.3), and L var If the threshold is less than the preset threshold, then left-side one-sided fitting will be used.

[0069] If the right lane line is invalid, the left lane line is valid, and the variance L between the left lane line and the historical trajectory line is... var If the value is less than a set threshold, the road centerline is still fitted based on the left lane line. For example, if the right lane line disappears for some reason, the left lane line remains clear and stable (L). var If the threshold is less than the preset threshold, then left-side one-sided fitting will also be used.

[0070] This comprehensive definition of when to trust and rely on the left lane line covers typical scenarios of uneven lanes on both sides and lanes on one side.

[0071] (c) If the right lane line is valid and the left lane line is valid, and the difference in variance weights between the two lane lines is greater than a set threshold, then if the variance R between the right lane line and the historical trajectory line is... var If the value is less than the set threshold, the road centerline will be fitted based on the right lane line.

[0072] If the right lane line is valid and the left lane line is invalid, and the variance R between the right lane line and the historical trajectory line is... var If the value is less than the set threshold, the road centerline is also fitted based on the right lane line.

[0073] This comprehensive definition of when to trust and rely on the right lane line, symmetrical to the left-side logic in (b), constitutes a complete one-sided fitting decision system.

[0074] (d) Except for the conditions mentioned in (a), (b) and (c) of step 2, lane line information is considered unavailable and lane center line is invalid in any other condition. To avoid accidental steering, lane following control will not be performed.

[0075] When approaching an intersection, except for the conditions mentioned in steps 2 (a), (b), and (c), the lane line information identified in any other condition is likely to be incorrect. To avoid accidental steering, the center line information is deemed invalid. At this time, the vehicle no longer performs lateral control based on lane line information. If there is a vehicle ahead and its trajectory meets the conditions, follow-the-car control is performed; if there is no vehicle ahead or its trajectory does not meet the conditions but the vehicle's status does, the cornering request hold logic is entered, and the lateral control function does not degrade to pass through the intersection; if none of the above conditions are met, the lateral function exits. The lane center line calculation logic when approaching an intersection can be found in [reference needed]. Figure 2 .

[0076] Step 2 proposes a comprehensive method for calculating lane centerlines under different working conditions when approaching an intersection. Based on a comprehensive evaluation of lane line effectiveness, lane line variance, and the weighted difference of lane line variance, the calculation is categorized into four types: lane centerline calculation based on both left and right lane lines, lane centerline calculation based on the left lane line, lane centerline calculation based on the right lane line, and lane centerline invalidation without following the lane line. This aims to minimize the degradation of lateral control function when passing through the intersection while avoiding accidental steering.

[0077] refer to Figure 3 Entering non-follow-the-line control mode (a mode that does not perform follow-the-line control), including:

[0078] The system determines if there is a vehicle ahead that meets the following criteria; if so, it switches to follow control mode. Specifically, when the lane center line is invalid, the system detects a vehicle traveling straight ahead at a constant speed and uses the trajectory of that vehicle as a reference for lateral control. This provides a preferred degraded control scheme, utilizing environmental vehicle information to maintain lateral assist functionality as much as possible.

[0079] If no vehicle is found that meets the following criteria, the corner hold logic is activated, and the lateral control function does not degrade to proceed through the intersection. Specifically, when there is no vehicle to follow, the system no longer seeks a new control target but maintains the steering wheel angle at the moment this method was triggered, allowing the vehicle to coast through the intersection in the current direction. This provides a secondary degraded solution. "Maintaining a straight course" is the safest and most predictable strategy when information is uncertain, avoiding driver panic caused by system exit.

[0080] When lane line data on one side is incomplete, the system first completes the data based on the complete lane line data on the other side and standard lane width information before performing a smoothness assessment. For example, if the right lane line is valid throughout, but the left lane line is missing at a distance, the system virtually generates a complete left lane line based on the position of the right lane line and the standard lane width of 3.75 meters, and then performs a smoothness analysis on this virtual line. This enhances the applicability and robustness of the lane centerline confirmation method in scenarios with incomplete perception information.

[0081] After adopting a one-sided fitting mode, the status of the other lane line is continuously monitored. When the other lane line becomes effective again and the difference in smoothness index between it and the currently used lane line is less than a first set threshold, the system smoothly switches to a two-sided fitting mode. For example, if the system is currently using a one-sided fitting mode on the right side due to the failure of the left lane, and then the left lane line is re-identified stably and the difference in variance weight between it and the right lane line is less than 0.2, the system will smoothly adjust the center line from the right to the center of the road over the next few control cycles. This achieves seamless switching of control modes, greatly improving the smoothness and comfort of the user experience.

[0082] refer to Figure 4The lane centerline confirmation method proposed in this application is implemented in the lateral control module of the vehicle's intelligent navigation assistance system. This lateral control module controls the vehicle's steering wheel angle in real time based on the lane centerline generated by the selected fitting mode or the command of the non-following control mode. The output of the entire decision-making process (a reliable lane centerline trajectory, or the commands "follow" or "maintain steering angle") is directly sent to the vehicle's lower-level actuators, realizing automatic lateral control of the vehicle. This clarifies the integration relationship and application method between the lane centerline confirmation method and the vehicle control system, forming a complete technical closed loop and demonstrating its industrial practicality.

[0083] In step 1, this application preliminarily assesses the effectiveness and smoothness of lane lines by evaluating lane line confidence and calculating the variance of lane lines on both sides of the lane. Steps (a), (b), and (c) in step 2 filter several operating conditions, and based on the effectiveness and smoothness of the left and right lane lines, three lane centerline calculation methods are established: fitting the lane centerline based on both left and right lane lines, fitting the lane centerline following the left lane line, and fitting the lane centerline following the right lane line. Finally, if the lane line recognition information and calculation results do not conform to the operating conditions described in steps (a), (b), and (c) of step 2, the lane centerline is considered invalid, and lateral control is not performed based on the lane line information. The lane centerline calculation method mentioned in this application avoids the problem of mis-steering due to inaccurate lane line recognition information when approaching an intersection, while also ensuring that lateral function does not degrade when passing through intersections, providing drivers with a better user experience.

[0084] This application decomposes complex intersection scenarios into finite, manageable conditions through a systematic two-level judgment (effectiveness and smoothness) and structured decision-making logic. This method not only fully utilizes high-quality lane information from both sides to achieve optimal control, but also maintains functionality without degradation when information from one side is reliable, and safely and gracefully degrades when information is completely unreliable. This forms a comprehensive solution covering everything from optimal to worst-case scenarios, fundamentally eliminating the possibility of mis-steering.

[0085] Based on the same inventive concept, embodiments of this application also provide an electronic device. Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of this application. Figure 5As shown in the figure, an electronic device provided in this application embodiment includes: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement any of the lane centerline confirmation methods in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory and configured to realize information interaction between the processor and the memory.

[0086] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0087] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0088] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0089] This application also provides a computer-readable medium. The computer-readable medium stores a computer program, which, when executed by a processor, implements the steps of any of the lane centerline confirmation methods described in the above embodiments. The computer-readable storage medium may be volatile or non-volatile.

[0090] This application also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the lane centerline confirmation method described above.

[0091] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0092] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0093] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0094] The computer program instructions used to perform the operations of this application may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuits, such as programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), are personalized by utilizing the status information of the computer-readable program instructions. These electronic circuits can execute the computer-readable program instructions to implement various aspects of this application.

[0095] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0096] Various aspects of this application are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0097] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0098] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0099] The flowcharts or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, or computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0100] Exemplary embodiments have been disclosed in this application, and while specific terminology has been used, it is used only and should be interpreted in a general illustrative sense and is not intended to be limiting. In some embodiments, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of this application as set forth by the appended claims.

Claims

1. A method for confirming lane centerline, characterized in that, include: The effectiveness and smoothness of the left and right lane lines are assessed separately. Based on the results of the validity and smoothness assessments, a centerline fitting mode is selected according to a preset decision logic; wherein, the decision logic includes: When the first condition is met, a two-sided fitting mode is adopted; When the second condition is met, the left-side one-sided fitting mode is adopted; When the third condition is met, the right-side one-sided fitting mode is adopted; If any of the above conditions are not met, the center line is deemed invalid, and the system enters non-following-line control mode.

2. The lane centerline confirmation method according to claim 1, characterized in that, The first condition is: The right lane line is valid, the left lane line is valid, and the difference in the smoothness index between the two lane lines is less than the first set threshold.

3. The lane centerline confirmation method according to claim 2, characterized in that, The second condition includes one or more of the following sub-conditions: The right lane line is valid, the left lane line is valid, the difference in the smoothness index of the two lane lines is greater than the first set threshold, and the smoothness of the left lane line is better than the set standard. The right lane markings are invalid, while the left lane markings are valid, and the smoothness of the left lane markings is better than the set standard.

4. The lane centerline confirmation method according to claim 2, characterized in that, The third condition includes one or more of the following sub-conditions: The right lane line is valid, the left lane line is valid, the difference in the smoothness index of the two lane lines is greater than the first set threshold, and the smoothness of the right lane line is better than the set standard. The right lane markings are valid, while the left lane markings are invalid, and the smoothness of the right lane markings is better than the set standard.

5. The lane centerline confirmation method according to any one of claims 1-4, characterized in that, In the dual-side fitting mode, the centerline confirmation strategy prioritizes the availability of the right lane line.

6. The lane centerline confirmation method according to claim 1, characterized in that, Entering the non-follow-the-line control mode includes: Determine if there is a vehicle ahead that meets the following conditions; if so, switch to following control mode.

7. The lane centerline confirmation method according to claim 6, characterized in that, The entry into non-follow-the-line control mode also includes: If there is no vehicle ahead that meets the following conditions, the corner holding logic is activated, and the lateral control function does not degrade to pass through the intersection.

8. The lane centerline confirmation method according to claim 1, characterized in that, The criteria for determining validity include: Whether the confidence level of the lane line provided by the sensor is higher than the preset confidence level threshold.

9. The lane centerline confirmation method according to claim 2, characterized in that, The smoothness assessment is achieved by calculating the variance of the lateral distance between the lane line and the vehicle's historical trajectory at multiple preset points. The smaller the variance, the smoother the lane line.

10. The lane centerline confirmation method according to claim 9, characterized in that, The smoothness index includes variance weight values. The formulas for calculating the variance weight values ​​of the left lane line and the right lane line are as follows: L vwv =L var / (L var +R var ); R vwv =R var / (L var +R var ); Among them, L var R represents the variance between the left lane line and the historical trajectory line. var L represents the variance between the right lane line and the historical trajectory line. vwv R represents the variance weight value of the left lane line; vwv This represents the variance weight value of the right lane line; the variance weight difference V vw =|L vwv -R vwv The smaller the variance weight difference, the more similar the smoothness of the lane lines on both sides.

11. The lane centerline confirmation method according to claim 1, characterized in that, When the lane line data on one side is incomplete, the data is first supplemented based on the complete lane line data on the other side and the standard lane width information, and then the smoothness judgment is made.

12. The lane centerline confirmation method according to claim 3 or 4, characterized in that, After adopting the single-sided fitting mode, the status of the other lane line is continuously monitored; when the other lane line becomes effective and the difference between the smoothness index of the lane line used and the lane line used is less than the first set threshold, the system smoothly switches to the double-sided fitting mode.

13. The lane centerline confirmation method according to claim 1, characterized in that, The lane centerline confirmation method is implemented in the lateral control module of the vehicle intelligent navigation assistance system. The lateral control module controls the steering wheel angle of the vehicle in real time based on the lane centerline generated by the selected fitting mode or the command of the non-following control mode.

14. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors are enabled to implement the steps in the lane centerline confirmation method as described in any one of claims 1 to 13.

15. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it can implement the steps in the lane centerline confirmation method as described in any one of claims 1 to 13.

Images