Vehicle lane changing control method, device, equipment, medium and program product

Abstract

The embodiment of the invention provides a vehicle lane changing control method and device, equipment, a medium and a program product. The method comprises the following steps: acquiring a road image collected by a visual sensor in an auxiliary driving mode; based on the road image, constructing a lane topology model, based on the lane topology model, identifying lane type information of a lane section where a vehicle is currently located or a lane section where the vehicle will enter after extending a first distance along the current lane, and determining whether the lane type information is a non-waiting-to-turn area; if yes, active lane changing operation triggered by the shifting rod signal is executed. In the process, the lane topology model fused with the multi-dimensional road semantic information is constructed, and the lane type information of the current and about-to-enter lane sections of the vehicle is subjected to refined identification and judgment based on the model, so that the special function areas such as the turn waiting area can be accurately distinguished. The method is used for achieving the effects of improving the accuracy and safety of the lane changing decision of the vehicle in the complex road environment and improving the user experience.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle lane change control method, device, equipment, medium, and program product. Background Technology

[0002] With the continuous development of driver assistance systems, the lever-triggered automatic lane change function allows drivers to make the vehicle automatically change lanes with simple operation.

[0003] Existing automatic lane-changing methods acquire road images and identify physical conditions such as lane line type, geometric parameters, and distance to other vehicles. Based on these perception results, a lane environment model around the vehicle is constructed, and corresponding judgment thresholds are set. When the driver triggers a lane-changing command, the system verifies whether these physical conditions meet the preset requirements to determine whether to execute an automatic lane change.

[0004] However, in complex urban road environments (such as complex intersections with multiple guide lanes or waiting areas), existing methods may execute lane changes simply because dashed lane lines are detected and physical conditions are met, which can easily lead to false lane changes that conflict with the driver's true intentions. Summary of the Invention

[0005] This application provides vehicle lane change control methods, devices, equipment, media, and program products to improve the accuracy and reliability of automatic lane change control and enhance driving safety.

[0006] In a first aspect, embodiments of this application provide a vehicle lane change control method, including:

[0007] In assisted driving mode, road images are acquired by visual sensors;

[0008] Based on road images, a lane topology model is constructed, which includes lane line type information, lane line location information, lane type information, and ground marking information.

[0009] Determining whether to execute an active lane change operation triggered by a lever signal based on a lane topology model includes:

[0010] Identify the lane type information of the lane segment where the vehicle is currently located, or the lane segment into which the vehicle will enter after extending a first distance along the current lane, and determine whether the lane type information is a non-waiting zone.

[0011] If so, then an active lane change operation triggered by the lever signal will be executed.

[0012] Optionally, when determining whether to perform an active lane change operation triggered by the lever signal based on the lane topology model, the method further includes:

[0013] When the lane type information of the lane segment in which the vehicle is currently located, or the lane segment into which the vehicle will enter after extending a first distance along the current lane, is determined to be a non-prohibited turning zone; and / or,

[0014] When the lane type information to be changed is determined to be a dashed line or a dashed-solid line, an active lane change operation triggered by the lever signal is executed. The lane to be changed refers to the lane line that crosses the target boundary laterally when the vehicle changes from the current lane to the target lane. The target lane is determined based on the lever signal.

[0015] Optionally, when determining whether to perform an active lane change operation triggered by the lever signal based on the lane topology model, the method further includes:

[0016] The visible length of the target lane, as well as the widths of the current lane and the target lane, are determined based on the lane topology model.

[0017] If the visible length of the target lane is greater than the preset visibility distance; and / or,

[0018] The width of both the current lane and the target lane is greater than the preset width;

[0019] Then, an active lane change operation triggered by the lever signal will be executed.

[0020] Optionally, when determining whether to perform an active lane change operation triggered by the lever signal based on the lane topology model, the method further includes:

[0021] Curvature information of the current lane or target lane is obtained based on the lane topology model;

[0022] Based on the vehicle's current speed and curvature information, determine whether the preset safety conditions for changing lanes on a curve are met.

[0023] If the conditions are met, an active lane change operation triggered by the lever signal will be executed.

[0024] Optionally, the preset safety conditions for changing lanes on curves include:

[0025] The curvature information of the current lane or the target lane is less than a preset curvature threshold; and / or,

[0026] The product of the vehicle's current speed and curvature information is less than the preset dynamic stability threshold.

[0027] Optionally, determining whether to perform an active lane change operation triggered by the lever signal based on the lane topology model also includes:

[0028] When navigation intent information is obtained, and the navigation intent information indicates going straight, turning left, or turning right, if the vehicle is not currently in the corresponding straight lane, left-turn lane, or right-turn lane, it will respond to the received lever signal and control the vehicle to perform an active lane change operation to change lanes to the corresponding lane.

[0029] Secondly, embodiments of this application provide a vehicle lane change control device, comprising:

[0030] The acquisition module is used to acquire road images collected by the vision sensor in assisted driving mode;

[0031] The processing module is used to construct a lane topology model based on road images. The lane topology model includes lane line type information, lane line location information, lane type information, and ground marking information.

[0032] The processing module is also used to determine whether to perform an active lane change operation triggered by the lever signal based on the lane topology model, including:

[0033] Identify the lane type information of the lane segment where the vehicle is currently located, or the lane segment into which the vehicle will enter after extending a first distance along the current lane, and determine whether the lane type information is a non-waiting zone.

[0034] If so, then an active lane change operation triggered by the lever signal will be executed.

[0035] Optionally, the processing module is further configured to, when determining that the lane type information of the lane segment where the vehicle is currently located, or the lane segment into which the vehicle will enter after extending a first distance along the current lane, is a non-prohibited turning zone; and / or,

[0036] When the lane type information to be changed is determined to be a dashed line or a dashed-solid line, an active lane change operation triggered by the lever signal is executed. The lane to be changed refers to the lane line that crosses the target boundary laterally when the vehicle changes from the current lane to the target lane. The target lane is determined based on the lever signal.

[0037] Optionally, the processing module is also used to determine the visible length of the target lane, as well as the width of the current lane and the target lane, based on the lane topology model;

[0038] If the visible length of the target lane is greater than the preset visibility distance; and / or,

[0039] The width of both the current lane and the target lane is greater than the preset width;

[0040] Then, an active lane change operation triggered by the lever signal will be executed.

[0041] Optionally, the processing module is also used to obtain curvature information of the current lane or the target lane based on the lane topology model;

[0042] Based on the vehicle's current speed and curvature information, determine whether the preset safety conditions for changing lanes on a curve are met.

[0043] If the conditions are met, an active lane change operation triggered by the lever signal will be executed.

[0044] Optionally, the preset safety conditions for changing lanes on curves include:

[0045] The curvature information of the current lane or the target lane is less than a preset curvature threshold; and / or,

[0046] The product of the vehicle's current speed and curvature information is less than the preset dynamic stability threshold.

[0047] Optionally, the processing module is further configured to, upon obtaining navigation intent information and the navigation intent information indicating straight, left turn, or right turn, if the vehicle is not currently in the corresponding straight lane, left turn lane, or right turn lane, control the vehicle to perform an active lane change operation to change lanes to the corresponding lane in response to the received lever signal.

[0048] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0049] The memory stores the instructions that the computer executes;

[0050] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0051] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0052] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0053] The vehicle lane change control method, device, equipment, medium, and program product provided in this application acquires road images collected by a visual sensor in assisted driving mode; constructs a lane topology model based on the road images, the lane topology model including lane line type information, lane line position information, lane type information, and ground marking information; and determines whether to execute an active lane change operation triggered by a lever signal based on the lane topology model, including: identifying the lane type information of the lane segment where the vehicle is currently located, or the lane segment into which the vehicle will enter after extending a first distance along the current lane, and determining whether the lane type information is a non-turning zone; if so, then executing an active lane change operation triggered by a lever signal. In this process, by constructing a lane topology model that integrates multi-dimensional road semantic information, and by performing refined identification and judgment of lane type information of the current and upcoming lane segments based on the model, it is possible to accurately identify special functional areas such as waiting-to-turn zones. This avoids executing lane change requests caused by misjudging lane functions, effectively solving the problem that the lever lane change function in existing assisted driving systems, in complex scenarios such as near intersections, lacks semantic understanding of lane functions (e.g., waiting-to-turn zones), and misjudges the driver's intention to enter a specific functional lane as a normal lane change command, leading to dangerous lane change operations that violate traffic rules and driving intentions. This achieves the effect of improving the accuracy, safety, and user experience of lane change decisions in complex road environments. Attached Figure Description

[0054] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0055] Figure 1 A schematic diagram illustrating a scenario for the vehicle lane change control method provided in this application;

[0056] Figure 2 A flowchart illustrating the vehicle lane change control method provided in this application;

[0057] Figure 3 A schematic diagram of the vehicle lane change control device provided in this application;

[0058] Figure 4 A schematic diagram of the structure of the electronic device provided in this application.

[0059] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0060] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0061] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation portals for users to choose to authorize or refuse.

[0062] With the rapid development of autonomous driving technology, the lane change function has become one of the core auxiliary functions of intelligent driving systems. This function triggers the vehicle to automatically complete the lane change operation by the driver moving the steering lever, and is widely used on highways, urban expressways, and some complex road conditions.

[0063] Currently, the lane-changing function in existing driver assistance systems primarily relies on the vehicle's onboard vision sensors. This involves capturing road images via cameras and determining lane-change feasibility based on lane line recognition. However, this existing technology still has limitations when dealing with certain complex road scenarios. For example, in situations like... Figure 1 In the intersection scene shown, the road has multiple waiting areas with different functions (i.e., Figure 1 (The straight-ahead waiting area and the left-turn waiting area are adjacent). In this scenario, as a vehicle approaches an intersection, lane markings typically guide it into the corresponding waiting area. If, at this point, the driver intends to enter the straight-ahead waiting area and habitually activates their left turn signal, existing technology, based on the logic that the left lane marking is dashed and the physical conditions are met, will mislead the vehicle into the left-turn waiting area instead of the straight-ahead waiting area the driver actually intends to enter. Therefore, existing technology easily confuses driving intentions, leading to incorrect lane changes that conflict with the driver's true intentions, impacting driving safety and user experience.

[0064] The vehicle lane change control method provided in this application acquires road images collected by a visual sensor in assisted driving mode; based on the road images, a lane topology model is constructed, including lane line type information, lane line position information, lane type information, and ground marking information; based on the lane topology model, a judgment logic determines whether to execute an active lane change operation triggered by a lever signal. Specifically, it identifies the lane type of the current lane segment, or the lane segment the vehicle will enter after extending a first distance along the current lane, and determines whether the lane type is a non-turning zone. If it is determined to be a non-turning zone, the vehicle is controlled to execute an active lane change operation. This effectively solves the problem of false triggering of the lever lane change function in complex intersection scenarios containing turning zones, improves the robustness of the system in complex environments, enhances the safety of lane change operations, and avoids potential risks caused by lane line recognition errors.

[0065] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0066] This application provides a vehicle lane change control method, device, equipment, medium, and program product, applied to a vehicle's driver assistance system. The driver assistance system includes components such as a vision sensor, an input interface, a controller, a navigation module, and actuators. For example, when a driver operates a lever in driver assistance mode, the input interface sends a lever signal to the controller. To avoid accidental lane changes that contradict the driver's true intentions or violate traffic rules in complex road scenarios such as turning areas and curves, the controller needs to judge the lever signal according to the vehicle lane change control method provided in this application, thereby deciding whether to control the actuator to perform an active lane change operation.

[0067] Figure 2 This is a flowchart illustrating the vehicle lane change control method provided in this application, such as... Figure 2 As shown, the method includes:

[0068] S201. In assisted driving mode, acquire road images collected by vision sensors.

[0069] More specifically, in assisted driving mode, the vehicle continuously acquires road images of the environment in front of and to the sides of the vehicle using visual sensors such as forward or side cameras mounted on the vehicle body. These road images include lane lines for defining lanes, ground directional arrows, text markings (e.g., left turn, bus lane), stop lines, and other road markings that may influence driving decisions. The acquired road images serve as the raw input for subsequent environmental perception and decision-making.

[0070] Optionally, the driver assistance modes include, but are not limited to, LCC (Lane Centering Control), ICC (Integrated Cruise Control), and NOA (Navigate on Autopilot).

[0071] S202. Based on road images, construct a lane topology model, which includes lane line type information, lane line location information, lane type information, and ground marking information.

[0072] More specifically, by performing image processing and recognition on the road images obtained in step S201, key road semantic information is extracted and organized using a structured data model. For example, based on the recognition results, a topological network describing the spatial connection and semantic attributes of the vehicle and its surrounding lanes is constructed, using the rear axle center of the vehicle as the reference origin; this is known as a lane topology model.

[0073] For example, by processing and recognizing road images, information such as lane lines and ground markings is extracted. Using the center point of the vehicle's rear axle as the reference origin, a three-lane topology model is constructed, comprising the vehicle's left lane, its own lane, and its right lane. Optionally, the lane topology model includes lane line type information, lane line location information, lane type information, and ground marking information. Lane line type information refers to the shape of the lane lines, such as dashed lines, solid lines, or a combination of both; lane line location information refers to the specific position of the lane lines in the vehicle coordinate system; lane type information refers to the functional attributes of the lanes, such as straight-ahead lanes, left-turn lanes, right-turn lanes, U-turn lanes, and waiting areas; and ground marking information refers to various markings on the road surface, such as directional arrows, text markings, and stop lines.

[0074] Optionally, when constructing the lane topology model, the parameter thresholds of the lane line type recognition algorithm used to construct the lane topology model are dynamically adjusted based on the current environmental perception data; the environmental perception data includes at least one of lighting conditions, weather information, and image clarity.

[0075] More specifically, accurate lane line identification is fundamental to building a reliable topology model. Image quality can easily degrade under different environmental conditions (e.g., nighttime, dusk, rain, snow, fog), leading to reduced performance of recognition algorithms with fixed parameters. Therefore, this method addresses this issue by introducing an environment-adaptive mechanism.

[0076] In one possible embodiment, ambient light sensor and rain sensor data are acquired in real time, and the signal-to-noise ratio of the acquired images is calculated. For example, when entering a tunnel or in a nighttime scene, if the ambient light level is detected to be lower than a preset light threshold, the contrast threshold of the lane line edge detection algorithm is automatically lowered, and the Gamma correction intensity in the image preprocessing stage is enhanced to improve lane line visibility in low light. In rainy or snowy weather, multi-frame image fusion technology is used. By statistically analyzing the lane line positions in multiple consecutive frames of images, instantaneous noise interference caused by raindrops or snowflakes is filtered out, thereby improving the stability and accuracy of lane line recognition results.

[0077] This embodiment improves the robustness and accuracy of lane topology model construction under adverse weather and complex lighting conditions by dynamically adjusting perception algorithm parameters according to environmental changes. This enhances the reliability of the road semantic map upon which subsequent lane-changing decisions rely, reducing decision-making errors caused by perception mistakes (such as misjudging solid lines as dashed lines or failing to identify the boundary of the turning zone) at the source.

[0078] S203. Determine whether to execute an active lane change operation triggered by the lever signal based on the lane topology model.

[0079] More specifically, by querying the lane topology model constructed in step S202, the lane type information of the lane segment where the vehicle is currently located, or the lane segment into which the vehicle will enter after extending a first distance along the current lane, is identified, and it is determined whether the lane type information is a non-turning zone; if so, an active lane change operation triggered by the lever signal is executed.

[0080] In one possible embodiment, such as Figure 1 As shown, when the driver activates the left turn signal lever, based on the lane topology model, the system identifies the lane type information of the lane segment that the vehicle is about to enter 50 meters ahead of its current lane (the first distance) as the second waiting area (i.e., the left turn waiting area). Since the left turn waiting area is a waiting area, the lane change operation is refused.

[0081] Optionally, when determining whether to execute an active lane change operation triggered by a lever signal based on the lane topology model, the method further includes: when the lane type information of the lane segment where the vehicle is currently located, or the lane segment into which the vehicle will enter after extending a first distance along the current lane, is determined to be a non-prohibited turning zone; and / or, when the lane line type information of the lane to be changed is determined to be a dashed line or a dashed-solid line, the active lane change operation triggered by the lever signal is executed, wherein the lane line to be changed refers to the lane line that crosses the target boundary laterally when the vehicle changes from the current lane to the target lane, and the target lane is determined based on the lever signal. In one possible embodiment, when the vehicle issues a lever signal to change lanes to the left, if it is determined that the lane type information of the lane segment where the vehicle is currently located is a non-prohibited turning zone, and the lane line type information of the lane to be changed on the left side of the vehicle is identified as a dashed line (or a dashed-solid line), then the execution of this left lane change operation is permitted.

[0082] In one possible embodiment, if the lane type information of the current lane segment is detected as a no-turn zone (e.g., emergency lane), or the lane type information of the lane to be changed to on the left side of the vehicle is identified as a solid line, then the left lane change operation is refused.

[0083] This embodiment combines lane function attributes (i.e. whether turning is prohibited) with lane line rules (dashed and solid lines) for verification, effectively avoiding accidental lane changes in areas where turning is prohibited, such as emergency lanes and bus lanes, or in solid line sections.

[0084] Optionally, when determining whether to perform an active lane change operation triggered by the lever signal based on the lane topology model, the method further includes: determining the visible length of the target lane and the widths of the current lane and the target lane based on the lane topology model; if the visible length of the target lane is greater than a preset visible distance; and / or, the widths of the current lane and the target lane are both greater than a preset width; then the active lane change operation triggered by the lever signal is performed.

[0085] Optionally, the preset width is determined based on the vehicle width, and the preset visibility distance can be dynamically calculated using the formula V*T, where V is the vehicle speed (m / s) and T is the lane change completion time recommended by the national standard (e.g., 5 seconds), thereby ensuring sufficient forward observation and operation space during the lane change process.

[0086] For example, the preset width can be set to 2.5 meters to ensure that the target lane can provide sufficient lateral safety space for vehicles.

[0087] In one possible implementation, when the driver activates the right turn signal to request a right lane change, the lane line adjacent to the vehicle's right side is determined as the lane to be changed to, based on the direction of the turn signal, and the lane adjacent to the vehicle's right side is designated as the target lane. Subsequently, the visible length of the target lane within a preset time (e.g., 5 seconds) is determined based on a lane topology model, and the widths of the current lane and the target lane are determined. If the visible length ahead of the target lane is insufficient due to weather conditions (e.g., less than the distance of vehicle speed × 5 seconds), or if either lane is too narrow (e.g., less than a preset width of 2.5 meters), the lane change is rejected.

[0088] This embodiment introduces the assessment of the visible length and lane width of the target lane to ensure that the vehicle has sufficient forward visibility and lateral maneuvering space during lane change, effectively avoiding safety risks such as interruption during lane change, collision with adjacent vehicles, or unstable trajectory control caused by insufficient visibility or narrow lanes, thus improving the reliability of lane change actions.

[0089] Optionally, when determining whether to perform an active lane change operation triggered by a lever signal based on the lane topology model, the method further includes: obtaining curvature information of the current lane or target lane based on the lane topology model; determining whether preset safety conditions for lane change on curves are met based on the vehicle's current speed and curvature information; and if so, performing an active lane change operation triggered by a lever signal.

[0090] Optionally, the preset safety conditions for changing lanes on curves include: the curvature information of the current lane or the target lane is less than a preset curvature threshold; and / or, the product of the vehicle's current speed and curvature information is less than a preset dynamic stability threshold.

[0091] In one possible embodiment, the vehicle is traveling on a highway at a speed of 60 km / h (approximately 16.7 m / s), and the driver activates the left turn signal. The system determines that the lane type information of the current lane segment is not a waiting area for turning, the adjacent lane line to the left of the vehicle is a dashed line, the width of both the target lane and the current lane is 3.5 meters (i.e., greater than the preset width of 2.5 meters), the curvature information of the current lane is less than the preset curvature threshold (e.g., 1 / 500), and the visible length of the target lane within a preset time (e.g., 5 seconds) is 85 meters (i.e., greater than the preset visible distance of 16.7 m / s * 5 s). At this point, a left lane change operation is determined to be performed. In this embodiment, the lane width is less than 5 meters.

[0092] This embodiment provides an objective and measurable safety benchmark for automatic lane changing by setting and verifying the conditions for multi-level lane changing. This avoids dangerous lane changing situations caused by insufficient space, inadequate time windows, or excessively sharp curves, thus improving the underlying safety of the system.

[0093] Optionally, determining whether to perform an active lane change operation triggered by the lever signal based on the lane topology model further includes: when navigation intent information is obtained and the navigation intent information indicates going straight, turning left, or turning right, if the vehicle is not currently in the corresponding straight lane, left-turn lane, or right-turn lane, then in response to the received lever signal, controlling the vehicle to perform an active lane change operation to change lanes to the corresponding lane.

[0094] More specifically, the navigation intent information comes from the route planned by the in-vehicle navigation system, usually provided in the form of "turn left / right / straight ahead in XX meters". This method incorporates this intent information into the lane change decision. If navigation information cannot be obtained (e.g., navigation is not turned on), the method only relies on the conditions in the aforementioned embodiments to determine whether to perform a lane change operation; if it can be obtained, this layer of verification is added to ensure that the decision is consistent with the driver's driving journey goal.

[0095] In one possible implementation, when a vehicle is driving in a straight lane with navigation activated, the navigation system instructs the driver to turn right at an intersection 300 meters ahead. The driver then activates a lever to request a right lane change. In this scenario, if it is determined that the vehicle is not currently in the right-turn lane indicated by the navigation intent, the system responds to the received right lane change request by controlling the vehicle to change lanes to the right.

[0096] In one possible embodiment, the vehicle navigation intent is to go straight at the upcoming intersection, and the vehicle is currently in the left-turn lane when the driver activates the right turn signal. In this scenario, it is determined that the navigation intent indicates the vehicle should go straight, and the vehicle is not currently in the straight lane. Therefore, in response to the received right turn signal, the driver controls the vehicle to perform an active lane change operation to the right.

[0097] This embodiment actively identifies whether the vehicle's current lane corresponds to the navigation intent information, interpreting the driver's lever operation in this scenario as a request to correct the lane position. This achieves the prediction and assisted execution of the driver's potential intent, reducing the operational burden on the driver in complex road conditions to find and enter the correct lane, and enhancing the driving experience.

[0098] In one possible embodiment, in Figure 1 In the scenario shown, after the vehicle extends a first distance along the current lane, the lane type information of the lane segment the vehicle will enter is the second waiting area (i.e., the left turn waiting area). The lane type information of the lane segment corresponding to the first distance ahead of the vehicle in the left lane is the first waiting area (i.e., the U-turn waiting area). At this time, combined with the left turn indicated by the navigation intention information, it is further judged that the second waiting area corresponds to the indication of the navigation intention information. Therefore, the vehicle refuses to change lanes to the left, thus ensuring that the vehicle stays in the original lane and can correctly enter the left turn waiting area ahead.

[0099] This solution effectively avoids deviations from the driving route due to misunderstandings of the driver's intentions (e.g., misinterpreting a left turn lever instruction as a left lane change lever instruction), thus improving the accuracy and reliability of driving control.

[0100] S204. When it is determined that lane changing is permitted, control the vehicle to perform an active lane changing operation.

[0101] More specifically, when the judgment logic of step S203 finally outputs the decision result that allows lane changing, the vehicle's controller (e.g., the autonomous driving domain controller) will generate corresponding control commands and send them to the vehicle's steering system, drive system, and braking system to coordinate and control the vehicle to automatically complete the lane changing operation from the current lane to the target lane with a smooth and safe trajectory and speed.

[0102] The vehicle lane change control method provided in this application constructs a lane topology model and, based on this model, adopts different judgment conditions to achieve a multi-dimensional and structured evaluation of lane change feasibility. It can accurately identify the true lane change intention, effectively avoid executing erroneous lane change operations that conflict with the driver's true intention in complex intersection scenarios, improve the accuracy and reliability of vehicle lane change control, and effectively improve the user experience.

[0103] Figure 3 This is a structural schematic diagram of the vehicle lane change control device provided in this application, such as... Figure 3 As shown, the vehicle lane change control device 30 provided in this embodiment includes:

[0104] The acquisition module 301 is used to acquire road images collected by the vision sensor in assisted driving mode;

[0105] Processing module 302 is used to construct a lane topology model based on road images. The lane topology model includes lane line type information, lane line location information, lane type information, and ground marking information.

[0106] Processing module 302 is also used to determine whether to perform an active lane change operation triggered by the lever signal based on the lane topology model, including:

[0107] Identify the lane type information of the lane segment where the vehicle is currently located, or the lane segment into which the vehicle will enter after extending a first distance along the current lane, and determine whether the lane type information is a non-waiting zone.

[0108] If so, then an active lane change operation triggered by the lever signal will be executed.

[0109] Optionally, the processing module 302 is further configured to, when determining that the lane type information of the lane segment where the vehicle is currently located, or the lane segment into which the vehicle will enter after extending a first distance along the current lane, is a non-prohibited turning zone; and / or,

[0110] When the lane type information to be changed is determined to be a dashed line or a dashed-solid line, an active lane change operation triggered by the lever signal is executed. The lane to be changed refers to the lane line that crosses the target boundary laterally when the vehicle changes from the current lane to the target lane. The target lane is determined based on the lever signal.

[0111] Optionally, the processing module 302 is also used to determine the visible length of the target lane, as well as the width of the current lane and the target lane, based on the lane topology model;

[0112] If the visible length of the target lane is greater than the preset visibility distance; and / or,

[0113] The width of both the current lane and the target lane is greater than the preset width;

[0114] Then, an active lane change operation triggered by the lever signal will be executed.

[0115] Optionally, the processing module 302 is also used to obtain curvature information of the current lane or the target lane based on the lane topology model;

[0116] Based on the vehicle's current speed and curvature information, determine whether the preset safety conditions for changing lanes on a curve are met.

[0117] If the conditions are met, an active lane change operation triggered by the lever signal will be executed.

[0118] Optionally, the preset safety conditions for changing lanes on curves include:

[0119] The curvature information of the current lane or the target lane is less than a preset curvature threshold; and / or,

[0120] The product of the vehicle's current speed and curvature information is less than the preset dynamic stability threshold.

[0121] Optionally, the processing module 302 is further configured to, upon obtaining navigation intent information and the navigation intent information indicating straight, left turn, or right turn, if the vehicle is not currently in the corresponding straight lane, left turn lane, or right turn lane, control the vehicle to perform an active lane change operation to change lanes to the corresponding lane in response to the received lever signal.

[0122] The vehicle lane change control device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0123] Figure 4 A schematic diagram of the structure of the electronic device provided in this application. Figure 4As shown, the electronic device 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the device 40 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0124] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0125] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0126] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0127] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0128] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0129] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0130] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0131] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0132] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0133] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0134] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0135] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0136] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0137] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0138] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A vehicle lane change control method, characterized in that, include: In assisted driving mode, road images are acquired by visual sensors; Based on the road image, a lane topology model is constructed, which includes lane line type information, lane line location information, lane type information, and ground marking information. Determining whether to execute an active lane change operation triggered by a lever signal based on the lane topology model includes: Identify the lane type information of the lane segment where the vehicle is currently located, or the lane segment into which the vehicle will enter after extending a first distance along the current lane, and determine whether the lane type information is a non-turning zone; If so, then an active lane change operation triggered by the lever signal will be executed.

2. The method according to claim 1, characterized in that, When determining whether to execute an active lane change operation triggered by a lever signal based on the lane topology model, the method further includes: When the lane type information of the lane segment in which the vehicle is currently located, or the lane segment into which the vehicle will enter after extending a first distance along the current lane, is determined to be a non-prohibited turning zone; and / or, When the lane type information to be changed is determined to be a dashed line or a dashed-solid line, an active lane change operation triggered by the lever signal is executed. The lane to be changed refers to the lane line that crosses the target boundary laterally when the vehicle changes from the current lane to the target lane. The target lane is determined based on the lever signal.

3. The method according to claim 1 or 2, characterized in that, When determining whether to execute an active lane change operation triggered by a lever signal based on the lane topology model, the method further includes: The visible length of the target lane, as well as the widths of the current lane and the target lane, are determined based on the lane topology model. If the visible length of the target lane is greater than the preset visible distance; and / or, The width of both the current lane and the target lane is greater than the preset width; Then, an active lane change operation triggered by the lever signal will be executed.

4. The method according to claim 1, characterized in that, When determining whether to execute an active lane change operation triggered by a lever signal based on the lane topology model, the method further includes: The curvature information of the current lane or the target lane is obtained based on the lane topology model. Based on the vehicle's current speed and the curvature information, determine whether the preset safety conditions for changing lanes on a curve are met; If the conditions are met, an active lane change operation triggered by the lever signal is executed.

5. The method according to claim 4, characterized in that, The preset safety conditions for changing lanes on curves include: The curvature information of the current lane or the target lane is less than a preset curvature threshold; and / or, The product of the vehicle's current speed and the curvature information is less than a preset dynamic stability threshold.

6. The method according to claim 1, characterized in that, The process of determining whether to perform an active lane change operation triggered by the lever signal based on the lane topology model also includes: When navigation intent information is obtained, and the navigation intent information indicates going straight, turning left, or turning right, if the vehicle is not currently in the corresponding straight lane, left-turn lane, or right-turn lane, the vehicle is controlled to perform an active lane change operation to change lanes to the corresponding lane in response to the received lever signal.

7. A vehicle lane change control device, characterized in that, include: The acquisition module is used to acquire road images collected by the vision sensor in assisted driving mode; The processing module is used to construct a lane topology model based on the road image. The lane topology model includes lane line type information, lane line location information, lane type information, and ground marking information. The processing module is further configured to determine, based on the lane topology model, whether to perform an active lane change operation triggered by the lever signal, including: Identify the lane type information of the lane segment where the vehicle is currently located, or the lane segment into which the vehicle will enter after extending a first distance along the current lane, and determine whether the lane type information is a non-turning zone; If so, then an active lane change operation triggered by the lever signal will be executed.

8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-6.

Images