Method and system for generating a light carpet for vehicle lane change

Abstract

The application discloses a light carpet generation method and system for vehicle lane changing, and the method comprises the following steps: acquiring body posture data of a driver; determining a first vehicle lateral deviation rate and a second vehicle lateral deviation rate of the vehicle according to first lane line information of a current lane of the vehicle; determining a running track and a running track curvature of the vehicle according to running state data of the vehicle; determining a target lane to be changed into by the vehicle according to the body posture data, the first vehicle lateral deviation rate, the second vehicle lateral deviation rate and the running track curvature; determining a plurality of target control points located on the target lane and the running track; generating a light carpet track according to the plurality of target control points, and controlling the target vehicle lamp to project a curved light carpet on the ground according to the light carpet track. The application can represent the running track and the lane changing intention of the vehicle through the light carpet when the ego vehicle starts to change lanes and has not yet invaded the adjacent lane, thereby improving the safety of night driving.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method and system for generating a light blanket for vehicle lane changes. Background Technology

[0002] At night, especially on high-risk road conditions like highways, drivers sometimes fail to use turn signals when changing lanes. This dangerous behavior not only endangers their own vehicle but also causes serious personal injury and property damage to other vehicles and drivers on the road. Because drivers' vision is limited in the dark, and audible alarms provide little information to drivers in other vehicles and are prone to misunderstanding, a light-based warning solution is urgently needed.

[0003] Current automotive lighting solutions typically use the vehicle's headlights to project a long strip of light in front of the vehicle, roughly the width of the vehicle itself. This light strip usually remains in a straight line or moves with changes in the lane ahead. However, this type of light strip has a very limited function; it can only aesthetically illuminate the lane ahead and lacks an effective warning mechanism for lane changes without using turn signals. It also struggles to accurately convey lane change information by combining driver intent with vehicle operating status, failing to meet the safety warning needs of high-risk road conditions at night. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method and system for generating a light carpet for vehicle lane changing. By acquiring driver body posture data, vehicle side offset rate relative to lane lines, and vehicle trajectory curvature, the target lane to be changed and the corresponding control point is determined. Based on the control point, a curve light carpet is generated and projected onto the ground to accurately convey the vehicle's lane changing intention. This effectively solves the safety warning problem of changing lanes at night without using turn signals, and improves the safety of nighttime driving and the accuracy of conveying lane changing intentions.

[0005] In a first aspect, embodiments of this application provide a method for generating a light blanket for vehicle lane changing, applied to a processor of a vehicle control system. The vehicle control system further includes a target headlight disposed in front of the vehicle, and the processor is connected to the target headlight. The method includes:

[0006] Acquire driver's body posture data;

[0007] The first vehicle side offset rate and the second vehicle side offset rate are determined based on the first lane line information of the lane where the vehicle is currently located. The first vehicle side offset rate represents the rate at which the left side of the vehicle moves toward the left lane line of the lane where the vehicle is currently located, and the second vehicle side offset rate represents the rate at which the right side of the vehicle moves toward the right lane line of the lane where the vehicle is currently located.

[0008] The vehicle's trajectory and trajectory curvature are determined based on the vehicle's operating status data;

[0009] The target lane into which the vehicle is to change lanes is determined based on the body posture data, the first vehicle side offset rate and the second vehicle side offset rate, and the curvature of the running trajectory.

[0010] Identify multiple target control points located on the target lane and the operating trajectory;

[0011] A light carpet trajectory is generated based on the multiple target control points, and the target vehicle lights are controlled to project onto the ground according to the light carpet trajectory to form a curved light carpet.

[0012] Secondly, this application also provides a vehicle control system, which includes a processor and a target headlight disposed in front of the vehicle, the processor being connected to the target headlight, wherein the system is used to execute the steps in the first aspect of the embodiments of this application.

[0013] Thirdly, embodiments of this application provide an electronic device, including a processing module, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processing module, and the programs include instructions for performing the steps in the first aspect of embodiments of this application.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in the first aspect of embodiments of this application.

[0015] Fifthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of embodiments of this application. The computer program product may be a software installation package.

[0016] As can be seen, the vehicle lane-changing light carpet generation method and system provided in this application involves the processor acquiring the driver's body posture data; determining the vehicle's first and second side offset rates based on the first lane line information of the vehicle's current lane; determining the vehicle's trajectory and trajectory curvature based on the vehicle's operating status data; determining the target lane the vehicle is about to change lanes into based on the body posture data, the first and second side offset rates, and the trajectory curvature; determining multiple target control points located on the target lane and trajectory; generating a light carpet trajectory based on the multiple target control points; and controlling the target headlights to project onto the ground according to the light carpet trajectory to form a curved light carpet. Thus, compared to existing light carpet solutions that only aesthetically illuminate the area in front of the vehicle, this application comprehensively determines the target lane for lane changing and generates a curved light carpet based on the driver's body posture data, the side offset rate relative to the lane line, and the vehicle's trajectory curvature, accurately conveying the vehicle's lane-changing intention. This effectively solves the safety warning problem of changing lanes at night without using turn signals, improving the safety of nighttime driving and the accuracy of conveying lane-changing intentions. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the architecture of a vehicle control system provided in an embodiment of this application;

[0019] Figure 2 This is a flowchart illustrating a method for generating a light blanket for vehicle lane changing, as provided in an embodiment of this application.

[0020] Figure 3 This is a schematic diagram illustrating the calculation of vehicle side offset rate according to an embodiment of this application;

[0021] Figure 4 This is a schematic diagram of a light carpet trajectory provided in an embodiment of this application;

[0022] Figure 5 This is a schematic diagram of a light carpet trajectory with the target lane being the current lane, provided in an embodiment of this application;

[0023] Figure 6 This is a schematic diagram of a light carpet trajectory where the target lane is the left adjacent lane, provided in an embodiment of this application;

[0024] Figure 7This is a schematic diagram of a light carpet trajectory where the target lane is the adjacent lane on the right, provided in an embodiment of this application;

[0025] Figure 8 This is a schematic diagram of a lighting scene for a vehicle traveling in the current lane, provided in an embodiment of this application.

[0026] Figure 9 This is a schematic diagram of another lighting scenario for a vehicle traveling in the current lane, provided in an embodiment of this application.

[0027] Figure 10 This is a schematic diagram of another lighting scenario for a vehicle traveling in the current lane, provided in an embodiment of this application;

[0028] Figure 11 This is a schematic diagram of a lighting scene for a vehicle changing lanes to the left, provided in an embodiment of this application;

[0029] Figure 12 This is a schematic diagram of a lighting scene for a vehicle changing lanes to the right, provided in an embodiment of this application;

[0030] Figure 13 This is a schematic diagram of a lighting scenario for vehicle driving when lane lines are unavailable, provided in an embodiment of this application.

[0031] Figure 14 This is a functional unit block diagram of a vehicle control system provided in an embodiment of this application;

[0032] Figure 15 This is a structural block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0033] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0034] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0035] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article indicates that the preceding and following related objects have an "or" relationship.

[0036] In this application's embodiments, "multiple" refers to two or more. In this application's embodiments, "connection" refers to various connection methods, such as direct or indirect connections, to achieve communication between devices; this application's embodiments do not impose any limitations on this.

[0037] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0038] The following describes the relevant content, concepts, meanings, technical issues, technical solutions, and beneficial effects involved in the embodiments of this application.

[0039] Current automotive lighting solutions typically use the vehicle's headlights to project a long strip of light in front of the vehicle, roughly the width of the vehicle itself. This light strip usually remains in a straight line or moves with changes in the lane ahead. However, this type of light strip has a very limited function; it can only aesthetically illuminate the lane ahead and lacks an effective warning mechanism for lane changes without using turn signals. It also struggles to accurately convey lane change information by combining driver intent with vehicle operating status, failing to meet the safety warning needs of high-risk road conditions at night.

[0040] To address the aforementioned issues, this application provides a method and system for generating a light carpet for vehicle lane changes. This method aims to comprehensively determine the target lane for lane changes and corresponding control points by acquiring driver body posture data, vehicle side offset rate relative to lane lines, and vehicle trajectory curvature. Based on these control points, a curved light carpet is generated and projected onto the ground to accurately convey the vehicle's lane-changing intention. This effectively solves the safety warning problem of lane changes without using turn signals at night, improving nighttime driving safety and the accuracy of conveying lane-changing intentions.

[0041] First, combined Figure 1 The vehicle control system in the embodiments of this application will be described. Figure 1 This is a schematic diagram of the architecture of a vehicle control system provided in an embodiment of this application, such as... Figure 1As shown, the vehicle control system 100 includes: a processor 110, a driver monitoring module 120, an environmental perception module 130, a vehicle pose module 140, and a target headlight 150 disposed in front of the vehicle. The processor 110 is communicatively connected to the driver monitoring module 120, the environmental perception module 130, the vehicle pose module 140, and the target headlight 150.

[0042] Specifically, the driver monitoring module 120 includes an in-vehicle camera 121, a head posture sensor 122, and an eye tracking sensor 123; the environmental perception module 130 includes a forward-looking vision sensor 131 and a millimeter-wave radar 132; and the vehicle posture module 140 includes an on-board positioning device 141 and an inertial measurement unit 142.

[0043] The driver monitoring module 120 is used to collect the driver's driving status and intentions, providing core subjective evidence for predicting lane change intentions. The in-vehicle camera 121 captures key postures such as head rotation (looking at the rearview mirror, looking back), facial orientation, and body movements by photographing the driver's face and upper body, serving as the basic hardware for identifying pre-lane change signs. The head posture sensor 122 accurately quantifies the head's pitch angle (looking down, looking up) and left and right rotation amplitude, supplementing the insufficient accuracy of the camera data and ensuring effective capture of subtle observation movements. The eye tracking sensor 123 monitors blink frequency, pupil size, and eye movement trajectory in real time, which not only helps determine whether the driver is distracted (such as looking away from the road or looking down at a mobile phone), but also further verifies the authenticity of the lane change intention by combining head movements, reducing the probability of misjudgment.

[0044] The environmental perception module 130 is used to acquire road environment information, mainly responsible for lane line detection and recognition. It provides environmental perception data for calculating the lateral distance (DLC, Distance from vehicle Lateral to Lane line, refers to the vertical physical distance from the side of the vehicle to the adjacent lane line, used to determine whether the vehicle deviates from the lane, crosses the line, etc.) and the derivative of distance (DDLC, Derivative of Distance from vehicle Lateral to Lane line, refers to the rate of change of the vehicle's lateral deviation relative to the lane line, reflecting how fast the vehicle approaches or moves away from the lane line, used to predict the risk of lane departure). The forward-looking vision sensor 131 captures images of the road in front of the vehicle, identifies the position and outline of the left and right lane lines through a visual algorithm, and obtains the actual physical distance by combining calibration parameters. The millimeter-wave radar 132 is used to assist in identifying road edges and reference objects in scenarios where the vision sensor is interfered with, improving the robustness of lane line detection.

[0045] The vehicle pose module 140 is used to acquire the vehicle's own position and motion attitude information, providing a basis for calculating the vehicle's trajectory curvature. The on-board positioning device 141, combined with a high-precision map, achieves lane-level precise positioning of the vehicle and outputs the vehicle's real-time position information; the inertial measurement unit 142 collects motion parameters such as the vehicle's heading angle, angular velocity, and lateral acceleration to calculate the vehicle's trajectory curvature, reflecting the vehicle's own driving trend.

[0046] The target headlight 150, positioned in front of the vehicle, serves as the execution terminal for the light carpet warning function, directly receiving light carpet trajectory control commands from the processor 110. Its core function is to project a smooth, curved light carpet onto the ground in front of the vehicle according to the trajectory parameters in the command. The shape and extension direction of the light carpet precisely match the trajectory parameters, intuitively conveying the vehicle's driving intentions and lane-changing direction.

[0047] The processor 110 is the core control unit of the system, which is used to receive and fuse three independent information sources: driver action intention information from the driver monitoring module 120, lane line related information from the environment perception module 130, and vehicle trajectory and posture information from the vehicle posture module 140. Based on the above three types of information, the processor 110 comprehensively determines the vehicle's lane change intention, calculates the target control point and the light carpet trajectory, and then controls the target headlight 150 to complete the light carpet projection.

[0048] As can be seen, in this embodiment, the vehicle control system accurately collects driver posture, lane lines and vehicle position posture data through the collaborative work of various modules. Relying on the processor to integrate the data and execute the core algorithm, it can accurately predict lane change intentions and reasonably determine the target lane and control point. Then, by using the target headlights to stably project a curve light carpet adapted to different scenarios, it can effectively convey driving and lane change intentions, improve nighttime driving safety and the accuracy of intention transmission, and ensure the stable operation of the vehicle in complex scenarios.

[0049] The following is combined with Figure 2 The method for generating a light blanket for vehicle lane changing, provided in the embodiments of this application, will be further described below. Please refer to... Figure 2 , Figure 2 This is a flowchart illustrating a method for generating a light blanket for vehicle lane changing, provided in an embodiment of this application. Figure 1 The processor 110 in the middle, such as Figure 2 As shown, the method includes the following steps:

[0050] Step S210: Obtain the driver's body posture data.

[0051] Among them, the driver's body posture data includes the driver's head rotation angle, face direction, upper body limb movements, head pitch, as well as blinking frequency, pupil size, eye movement trajectory, etc. These data can directly reflect whether the driver has any pre-lane change actions to observe road conditions to the left or right, and can also help determine whether the driver is in a state of distraction or fatigue.

[0052] Specifically, the in-vehicle camera captures images of the driver's face and upper body, extracting visual feature data such as head rotation, facial orientation, and body movements; the head posture sensor precisely quantifies the head's pitch angle and lateral rotation amplitude, supplementing the accuracy of the visual data; the eye-tracking sensor captures the driver's blink frequency, pupil changes, and eye movement trajectory in real time. All the collected raw data is transmitted to the processor in real time for initial integration and preprocessing.

[0053] Step S220: Determine the first vehicle side offset rate and the second vehicle side offset rate of the vehicle based on the first lane line information of the lane where the vehicle is currently located.

[0054] Wherein, the first vehicle side offset rate represents the rate at which the left side of the vehicle moves toward the left lane line of the lane in which the vehicle is currently located, and the second vehicle side offset rate represents the rate at which the right side of the vehicle moves toward the right lane line of the lane in which the vehicle is currently located.

[0055] In one possible embodiment, determining the first and second vehicle side offset rates of the vehicle based on the first lane line information of the lane the vehicle is currently in includes: determining the left and right lane lines of the lane the vehicle is currently in based on the first lane line information; determining the first position of the left side of the vehicle and the second position of the right side of the vehicle based on the vehicle's current position and vehicle parameter information; calculating a first distance between the first position of the left side of the vehicle and the left lane line of the lane the vehicle is currently in at the current time point, and a second distance between the second position of the right side of the vehicle and the right lane line of the lane the vehicle is currently in; and calculating a third distance between the first position of the left side of the vehicle and the left lane line of the lane the vehicle is currently in at the previous time point, and a fourth distance between the second position of the right side of the vehicle and the right lane line of the lane the vehicle is currently in, wherein the time points between adjacent time points are a preset interval; obtaining the first vehicle side offset rate based on the ratio of the difference between the first and third distances to the preset interval; and obtaining the second vehicle side offset rate based on the ratio of the difference between the second and fourth distances to the preset interval.

[0056] The lane line information includes lane line location, lane line confidence level, lane line stability, and lane line length.

[0057] Specifically, lane line confidence is a quantitative indicator of the reliability of the identified lane lines by the algorithm; lane line stability is an indicator of the consistency and fluctuation of lane line identification results during continuous frame acquisition; lane line length is the actual coverage span of the identified lane line; and lane line position is the coordinate information of the lane line in a local coordinate system with the vehicle as the reference. All these data are obtained by acquiring images of the road ahead using the forward vision sensor of the vehicle ranging module, performing lane line detection and feature extraction through computer vision algorithms, and calibrating by combining attitude data from the inertial measurement unit and lane reference information from high-precision maps.

[0058] Specifically, in this embodiment, the lateral distance data between the vehicle's side and the lane lines at different time points is first acquired periodically at preset intervals. Then, the vehicle side offset rate is calculated by the ratio of the lateral distance difference to the preset interval. The acquisition process relies on the multi-hardware collaboration of the vehicle ranging module. The forward-looking vision sensor captures images of the road ahead in real time. The pixel positions of the left and right lane lines are identified through a visual algorithm. Combined with calibration parameters such as camera intrinsic and extrinsic parameters, the pixel-dimensional distance is converted into a first and second physical distance. Then, the distance difference between the current time point and the previous time point is divided by the preset interval to obtain the first and second vehicle side offset rates, which represent the speed and direction of the vehicle's left and right sides relative to the lane lines.

[0059] For example, assuming the preset interval is 0.1 seconds, the first distance collected at the current time node is 1.0 meter, and the third distance corresponding to the previous time node is 1.2 meters, then the calculation process of the first vehicle side offset rate is (1.0 meter - 1.2 meter) ÷ 0.1 seconds = -2 meters / second. A negative first vehicle side offset rate indicates that the left side of the vehicle is moving towards the left lane line. If the first distance collected at the current time node is 1.1 meters, and the third distance corresponding to the previous time node is 1.0 meter, then the corresponding first vehicle side offset rate is (1.1 meter - 1.0 meter) ÷ 0.1 seconds = 1 meter / second. A positive first vehicle side offset rate indicates that the left side of the vehicle is moving away from the left lane line.

[0060] Specifically, a scenario diagram for obtaining the lateral distance between the vehicle and the lane line can be found in [reference needed]. Figure 3 , Figure 3 This is a schematic diagram illustrating the calculation of vehicle side offset rate provided in an embodiment of this application, as shown below. Figure 3As shown, the vehicle is in the current lane. The first distance represents the left DLC, which is the lateral distance between the left side of the vehicle and the left lane line. The second distance represents the right DLC, which is the lateral distance between the right side of the vehicle and the right lane line.

[0061] At each time point, the system synchronously acquires the first distance and the second distance. By comparing the distance difference between the two time points with a preset interval, the system obtains the first vehicle side offset rate relative to the left lane line and the second vehicle side offset rate relative to the right lane line. For example, when the vehicle changes lanes to the left, the first distance continuously shortens, and the calculated first vehicle side offset rate is negative, intuitively reflecting the vehicle's movement trend towards the left lane line. If the vehicle corrects its position to the right, the second distance changes accordingly, and the corresponding second vehicle side offset rate is updated synchronously, providing objective displacement data support for subsequent lane change intention determination.

[0062] As can be seen, in this embodiment, by accurately calculating the vehicle side offset rate and the curvature of the running trajectory, the lateral movement trend and steering characteristics of the vehicle are captured in real time, providing reliable running status data support for subsequent lane change intention determination and light carpet trajectory generation, effectively improving the accuracy and scene adaptability of nighttime lane change warning.

[0063] Step S230: Determine the vehicle's operating trajectory and trajectory curvature based on the vehicle's operating status data.

[0064] Among them, the curvature of the running trajectory is a physical quantity that describes the degree and direction of the curvature of the vehicle's driving trajectory. Its positive and negative values ​​correspond to the left and right curvature directions of the trajectory, and the magnitude of the value reflects the curvature. It is the core parameter for judging the vehicle's lane change or turning status.

[0065] In one possible embodiment, determining the vehicle's trajectory and trajectory curvature based on the vehicle's operating status data includes: determining the vehicle's driving position, steering angular rate, and steering wheel angle based on the vehicle's operating status data; determining the vehicle's trajectory based on the vehicle's driving position; calculating a first trajectory curvature based on the vehicle's steering angular rate; and calculating a second trajectory curvature based on the vehicle's steering wheel angle; and weighting and summing the first trajectory curvature and the second trajectory curvature according to a first preset weight and a second preset weight to obtain the vehicle's trajectory curvature.

[0066] Specifically, in this embodiment, the first trajectory curvature is calculated based on a high-speed dynamic model using the steering angle rate. This model is adapted to high-speed scenarios and reflects the trajectory changes caused by agile steering at high speeds in real time by combining the steering angle rate with dynamic parameters such as vehicle speed. The second trajectory curvature is calculated based on a static two-wheeled vehicle model using the steering wheel angle. This model is adapted to low-speed scenarios and directly derives the correspondence between the steering wheel angle and trajectory curvature at low speeds using fixed parameters such as steering wheel angle, steering ratio, and vehicle wheelbase. The two models are adapted to the steering characteristics at different vehicle speeds, and the final curvature is obtained through weighted fusion, balancing the needs of high-speed dynamic response and low-speed static accuracy. The weights are dynamically allocated based on the vehicle's current speed between 0 and 1. The core principle is to tilt the weights towards the model that is more suitable for the current vehicle speed. When the vehicle speed is high, the weight of the high-speed model will increase accordingly; when the vehicle speed is low, the weight of the static two-wheeled vehicle model will increase.

[0067] For example, assuming the vehicle's current speed is 70 km / h, which is a high-speed scenario, the first preset weight is set to 0.8 and the second preset weight is set to 0.2. If the curvature of the first trajectory calculated by the high-speed model is 0.02 rad / m and the curvature of the second trajectory calculated by the static model is 0.01 rad / m, the final trajectory curvature after weighted summation is 0.8 × 0.02 + 0.2 × 0.01 = 0.018 rad / m.

[0068] It should be noted that this application only provides a method for calculating the curvature of a vehicle's trajectory, but does not limit the use of other equivalent or improved technical solutions to achieve the same curvature calculation effect. As long as the bending characteristics of the vehicle trajectory can be accurately captured, they all fall within the scope of the technical concept protected by this application.

[0069] Step S240: Determine the target lane into which the vehicle is to change lanes based on the body posture data, the first vehicle side offset rate and the second vehicle side offset rate, and the curvature of the running trajectory.

[0070] The target lane includes the lane to the left of the lane the vehicle is currently in, the lane to the right of the lane the vehicle is currently in, and the lane the vehicle is currently in.

[0071] In one possible embodiment, determining the target lane the vehicle is to change lanes into based on the body posture data, the first vehicle side offset rate, the second vehicle side offset rate, and the curvature of the running trajectory includes: determining a first intended lane observed by the driver for the lane change based on the body posture data; determining a second intended lane for the vehicle to change lanes into based on the first vehicle side offset rate and the second vehicle side offset rate; determining a third intended lane for the vehicle to change lanes into based on the curvature of the running trajectory; if at least two of the first intended lane, the second intended lane, and the third intended lane are adjacent lanes on the same direction side of the vehicle's current lane, then the adjacent lane on the same direction side is determined as the target lane the vehicle is to change lanes into, wherein the adjacent lane on the same direction side is either the left adjacent lane or the right adjacent lane; otherwise, the vehicle's current lane is determined as the target lane the vehicle is to change lanes into.

[0072] In this embodiment, the target lane is determined by combining three dimensions: the driver's subjective intention, the vehicle's objective displacement state, and the vehicle's trajectory trend. Specifically, the subjective lane-changing intention is extracted from the driver's body posture (first intended lane), the actual vehicle displacement intention is extracted from the vehicle's side offset rate (second intended lane), and the vehicle's turning trend intention is extracted from the curvature of the running trajectory (third intended lane). The final target lane is then output through a consistency check.

[0073] Specifically, “determining the adjacent lanes on the same direction side as the target lanes into which the vehicle is to change lanes” includes the following situations: (1) the first intended lane is the same as the second intended lane and is adjacent lane on the same side; (2) the first intended lane is the same as the third intended lane and is adjacent lane on the same side; (3) the second intended lane is the same as the third intended lane and is adjacent lane on the same side; (4) the three intended lanes are completely the same and are adjacent lanes on the same side.

[0074] Specifically, “determining the lane where the vehicle is currently located as the target lane into which the vehicle is to change lanes” includes the following situations: (1) the three intended lanes are completely different, for example, the first intended lane is the left adjacent lane, the second intended lane is the right adjacent lane, and the third intended lane is the current lane; (2) at most one intended lane points to an adjacent lane, and the rest are the current lane: for example, the first intended lane is the left adjacent lane, and the second and third intended lanes are both the current lanes.

[0075] In one possible embodiment, determining the first intended lane that the driver is observing to enter based on the body posture data includes: if the driver turns their head to the left and focuses their gaze on the left side of the area for a certain duration, determining that the first intended lane is the adjacent lane on the left; if the driver turns their head to the right and focuses their gaze on the right side of the area for a certain duration, determining that the first intended lane is the adjacent lane on the right; if there is no obvious turning action and the driver's gaze is directly forward, determining that the first intended lane is the current lane.

[0076] It should be noted that this application only provides a method for determining the first intended lane for lane changing based on body posture data, including but not limited to the judgment logic of combining head turning and line of sight. It can also be used to capture other body posture characteristics such as the driver's limb movements before lane changing, body tilt amplitude, and seat posture adjustment, or to integrate auxiliary data such as changes in driver attention for comprehensive judgment. As long as the technical solution is based on the driver's body posture characteristics to deduce the intention to change lanes, it falls within the scope of protection of this application.

[0077] In one possible embodiment, determining the second intended lane that the vehicle is about to enter based on the first vehicle side offset rate and the second vehicle side offset rate includes: if the first vehicle side offset rate is negative and the absolute value of the first vehicle side offset rate is greater than a preset rate, then the lane adjacent to the left of the vehicle's current lane is determined as the second intended lane; if the second vehicle side offset rate is negative and the absolute value of the second vehicle side offset rate is greater than the preset rate, then the lane adjacent to the right of the vehicle's current lane is determined as the second intended lane; otherwise, the vehicle's current lane is determined as the second intended lane.

[0078] Understandably, when the first vehicle side offset rate is negative and its absolute value exceeds the preset rate, it indicates that the left side of the vehicle is moving significantly closer to the left lane line, and the second intended lane is determined to be the adjacent lane on the left. When the second vehicle side offset rate is negative and its absolute value exceeds the preset rate, it indicates that the right side of the vehicle is moving significantly closer to the right lane line, and the second intended lane is determined to be the adjacent lane on the right. Similarly, when one vehicle side offset rate is negative, and the other vehicle side offset rate is positive at the same time point, it indicates that the other side of the vehicle is moving away from the other lane line. If neither of the above two conditions is met, it means that the vehicle does not have a significant tendency to move towards a certain adjacent lane, and the second intended lane is determined to be the current lane.

[0079] In one possible embodiment, determining the third intended lane for the vehicle to change lanes based on the curvature of the running trajectory includes: if the curvature of the running trajectory indicates that the vehicle's running trajectory is curved to the left, and the curvature of the running trajectory is greater than a preset curvature, then the lane adjacent to the left of the vehicle's current lane is determined as the third intended lane; if the curvature of the running trajectory indicates that the vehicle's running trajectory is curved to the right, and the curvature of the running trajectory is greater than the preset curvature, then the lane adjacent to the right of the vehicle's current lane is determined as the third intended lane; if the curvature of the running trajectory indicates that the vehicle's running trajectory is a straight line, and / or the curvature of the running trajectory is not greater than the preset curvature, then the lane the vehicle is currently in is determined as the third intended lane.

[0080] The curvature of the running trajectory is characterized by positive and negative signs to indicate the bending direction of the vehicle's running trajectory. Typically, a local coordinate system is established based on the vehicle's forward direction, with the left side of the vehicle set as the negative coordinate direction. If the calculated curvature of the running trajectory is negative, it indicates that the vehicle's running trajectory is bent to the left; if the curvature of the running trajectory is positive, it indicates that the vehicle's running trajectory is bent to the right.

[0081] As can be seen, in this embodiment, by integrating the intended lane information from three dimensions—driver's subjective intent, vehicle's objective displacement state, and vehicle trajectory trend—and employing multi-dimensional consistency verification logic to determine the target lane into which the vehicle is about to change lanes, the accuracy and reliability of lane change determination are improved. This determination logic can accurately identify the vehicle's lane change tendency and lane in complex scenarios where the vehicle begins to change lanes but has not yet encroached on the adjacent lane, providing timely decision-making basis for subsequent light carpet projection. This achieves early warning of lane change intent, overcoming the technical deficiency of existing technologies where the light carpet cannot effectively present information in such scenarios, and enhancing the timeliness and practicality of nighttime lane change warnings.

[0082] Step S250: Determine multiple target control points located on the target lane and the running trajectory.

[0083] Among them, the target control point is the key coordinate node for anchoring the projection trajectory of the light blanket.

[0084] In one possible embodiment, determining multiple target control points located on the target lane and the driving trajectory includes: determining a first light carpet guidance route within the target lane, the first light carpet guidance route including the lane centerline of the target lane; determining a first control point, a second control point, and a third control point and a fourth control point located on the driving trajectory, the first control point being located at the current position of the vehicle; and obtaining the multiple target control points based on the first control point, the second control point, the third control point, and the fourth control point.

[0085] In this embodiment, the selection of the first, second, third, and fourth control points is merely an exemplary scheme and does not limit the number of control points. In practical applications, the number of control points can be flexibly adjusted according to the vehicle driving scenario and the curvature of the running trajectory. For example, in high-speed lane-changing scenarios, the number of control points can be appropriately increased to ensure a smooth transition of the light carpet trajectory. In low-speed, small-angle lane-changing scenarios, the number of control points can be reduced to simplify calculations. As long as the current position of the vehicle, the direction of the running trajectory, and the position of the target lane can be anchored, the accuracy requirements for the generation of the light carpet trajectory can be met.

[0086] Understandably, the first light carpet guidance route selects the center line of the target lane because the center line is the core benchmark of the target lane, which can accurately mark the center position and extension direction of the target lane. Using this as a benchmark to determine the control point can ensure that the generated light carpet trajectory always fits the driving path of the target lane, allowing surrounding vehicles to clearly identify the end point of the vehicle's lane change. At the same time, the linear characteristics of the lane center line are more conducive to building a continuous and smooth light carpet guidance trajectory, avoiding misunderstanding of lane change intentions due to light carpet deviation, and improving the intuitiveness and effectiveness of the warning.

[0087] In one possible embodiment, determining the first control point, the second control point, and the third and fourth control points located on the operating trajectory and on the first light carpet guide route includes: determining the first coordinate of the first control point based on the current position of the vehicle, the first coordinate including a first abscissa and a first ordinate, the axial direction corresponding to the ordinate being the direction of a single lane extension, and the axial direction corresponding to the abscissa being parallel to the plane of the lane and perpendicular to the direction of the single lane extension; determining the second ordinate of the second control point based on the first ordinate and a first preset distance, and determining the coordinate point corresponding to the second ordinate on the operating trajectory as the second control point; determining the third ordinate of the third control point based on the first ordinate and a second preset distance, and determining the coordinate point corresponding to the third ordinate on the first light carpet guide route as the third control point; determining the fourth ordinate of the fourth control point based on the first ordinate and a third preset distance, and determining the coordinate point corresponding to the fourth ordinate on the first light carpet guide route as the fourth control point, wherein the values ​​of the first preset distance, the second preset distance, and the third preset distance increase sequentially.

[0088] Specifically, in this embodiment, by establishing a coordinate system with the lane extension direction as the vertical coordinate and the perpendicular direction of the lane as the horizontal coordinate, the coordinate determination rules for the four control points are clarified. The core logic is to arrange the control points in an orderly manner along the vehicle's driving and lane-changing path. The first control point is directly anchored to the vehicle's current position. The second control point is selected along the running trajectory at a first preset distance to ensure that it conforms to the real-time driving trend of the vehicle. The third and fourth control points are selected along the center line of the target lane at successively increasing second and third preset distances. This not only anchors the extension direction of the target lane, but also allows the control points to form a smooth transition path from the current position to the target lane through the increasing preset distance, providing an accurate coordinate reference for the subsequent generation of a continuous light carpet trajectory.

[0089] For example, assuming the vertical coordinate is along the lane extension direction and the horizontal coordinate is perpendicular to the lane extension direction and parallel to the lane surface, the current position of the vehicle, i.e., the coordinates of the first control point, is (2, 0), the first preset distance is 5, the second preset distance is 10, and the third preset distance is 15. Then, the vertical coordinate of the second control point is 0+5=5, and its coordinates are the point (2.2, 5) on the running trajectory corresponding to the vertical coordinate 5; the vertical coordinate of the third control point is 0+10=10, and its coordinates are the point (3, 10) on the center line of the target lane corresponding to the vertical coordinate 10; the vertical coordinate of the fourth control point is 0+15=15, and its coordinates are the point (3, 15) on the center line of the target lane corresponding to the vertical coordinate 15. Thus, four target control points are arranged in an orderly manner.

[0090] In one possible embodiment, before determining the first light carpet guidance route within the target lane, the method includes: determining the left and right lane lines of the target lane based on second lane line information of the target lane, wherein the lane line information includes lane line position, lane line confidence, lane line stability, and lane line length; determining, based on the second lane line information, that the left and right lane lines of the target lane are in a fully usable state, or determining, based on the second lane line information, that the left and / or right lane lines of the target lane are in a partially usable state, wherein the partially usable state indicates that some lane lines are temporarily missing, and then supplementing the partially missing lane lines based on the lane line status data corresponding to the left and / or right lane lines.

[0091] Understandably, before determining the first light carpet guidance route within the target lane, it is necessary to ensure the reliability of the lane line data for the target lane. Specifically, the left and right lane lines of the target lane are first accurately identified, and then four core state data points—lane line confidence, stability, length, and position—are extracted. Subsequently, two scenarios are processed: if the lane line status fully meets the usage requirements, it is directly determined to be complete and usable; if there is a temporary partial loss of lane lines but the remaining part still has reference value, it is determined to be partially usable and is supplemented to avoid subsequent light carpet guidance route deviation due to incomplete lane lines, thus ensuring the accuracy of lane change warnings.

[0092] In one example, to determine whether the left and right lane lines of a target lane are fully or partially usable, the collected lane line confidence, stability, length, and position data are compared with preset thresholds. If the confidence of both lane lines is higher than the preset confidence threshold, the stability shows no significant fluctuations and meets the stability threshold requirements, the length coverage meets the preset standard, and the position deviation from the standard lane line position is within the allowable range, then it is determined to be fully usable. If one or two lane lines are temporarily missing, but the remaining valid segment's status data is still within the preset threshold range, and the length of the missing segment does not exceed the allowable upper limit, then the left and / or right lane lines are determined to be partially usable.

[0093] Furthermore, missing lane lines can be supplemented using various methods based on lane line status data, including but not limited to the following: First, temporal interpolation supplementation, which uses historical data such as lane line position and stability collected from consecutive frames to fit the lane line trajectory of the missing segment in the current frame through interpolation algorithms; second, geometric feature fitting supplementation, which calculates and supplements the outline of the missing part based on the straight or curved features of the complete lane line segment, combined with parameters such as standard lane width and curvature; and third, map data fusion supplementation, which combines the target lane reference information pre-stored in the high-precision map with the existing lane line status data to calibrate and supplement the missing segment, ensuring that the supplemented lane line is consistent with the actual road features.

[0094] As can be seen, in this embodiment, by detecting the state of the left and right lane lines of the target lane and performing missing segment completion processing, the accurate lane line reference is directly used when the lane line is complete and usable, and the missing segment is completed based on the effective state data when the lane line is partially usable. This ensures the reliability of the target lane reference information and avoids the interference of temporary partial missing lane lines on the generation of subsequent light carpet guidance routes. It provides stable data support for constructing a light carpet trajectory that accurately fits the target lane, thereby improving the accuracy and consistency of lane change warning.

[0095] In one possible embodiment, the method further includes: determining, based on the second lane line information, that the left lane line and right lane line of the target lane are unavailable, then determining a first control point, a second control point, a third control point, and a fourth control point located on the running trajectory; and obtaining the plurality of target control points based on the first control point, the second control point, the third control point, and the fourth control point.

[0096] In one example, to determine if the left and right lane lines of a target lane are unusable, the four core status data of the collected lane lines—confidence, stability, length, and position—are compared with preset thresholds. When the confidence of the left and right lane lines is lower than the preset confidence threshold, the stability fluctuation exceeds the threshold range, the effective length does not reach the minimum preset standard, the deviation of the position from the standard lane line position exceeds the allowable range, or there is a large area of ​​missing lane lines, the status data of the remaining effective segments cannot meet the preset threshold requirements, and the length of the missing segments exceeds the allowable upper limit, the lane lines can be determined to be unusable.

[0097] It should be clarified that the embodiments of this application only provide a method for determining whether a lane line is in a fully usable, partially usable, or unusable state based on lane line state data. It does not limit the dimension of the state data and the specific algorithm logic on which the determination is based. It can also be comprehensively determined by fusing multi-source sensor data such as LiDAR point cloud data and vehicle millimeter-wave radar detection information, or by introducing extended dimensions such as lane line texture features and neighboring lane line association features extracted by deep learning semantic segmentation models. As long as the technical solution is based on lane line related state information to divide its usability state, it falls within the scope of protection of this application.

[0098] Understandably, when lane lines are fully or partially available, assigning four control points to both the vehicle's trajectory and the target lane's center line allows the control points to simultaneously anchor the vehicle's current driving trend and the endpoint of the lane change. Through the cooperation of these two types of control points, the generated light carpet trajectory ensures a smooth transition between the vehicle's current position and the target lane, clearly conveying the lane change intention. However, when lane lines are unavailable, the system cannot obtain reliable reference information for the target lane, and therefore cannot extract the relevant control points for the target lane's center line. In this case, all four control points are determined based on the driving trajectory, ensuring that the control point generation logic remains uninterrupted. This, in turn, ensures that the light carpet can still present the lane change direction based on the vehicle's own driving trajectory, maintaining the continuity of the lane change warning function.

[0099] As can be seen, in this embodiment, by performing multi-state determination of the target lane line as fully available, partially available, or unavailable, the problem of insufficient adaptability of the existing vehicle light carpet solution in complex scenarios such as missing lane lines and the initial stage of lane change is effectively solved. This ensures the accuracy of the light carpet trajectory and the continuity and stability of the lane change warning function, and can fully cover various actual driving scenarios.

[0100] Step S260: Generate a light carpet trajectory based on the multiple target control points, and control the target vehicle lights to project onto the ground according to the light carpet trajectory to form a curved light carpet.

[0101] Specifically, in this embodiment, based on multiple predetermined target control points, a smooth curve algorithm such as Bézier curves is used to fit a continuous light carpet trajectory that fits the lane change path. A Bézier curve is a parametric smooth curve; its core principle is to generate a continuous curve trajectory through weighted calculations of the positions of a finite number of control points. The shape of the curve is determined by the number and coordinates of the control points. The curve is influenced by the pull of all control points and will not exceed the range formed by the control points. By adjusting the spacing and arrangement of the control points, the curvature and smoothness of the curve can be precisely controlled. Only a small number of control points are needed to generate curved lines that meet the requirements of lane changes, adapting to the generation scenario of the light carpet trajectory.

[0102] Furthermore, when the target headlights project the curved light carpet along the light carpet trajectory, the vehicle control system first analyzes the coordinate parameters of the trajectory and converts them into projection angle and area commands for the headlights. Then, it controls the light source array or shading module of the headlights to precisely adjust the light on the ground area corresponding to the trajectory. That is, it outputs high-brightness light to the area within the trajectory range, while reducing the brightness or turning off the light source in the area outside the range. Finally, a curved light carpet that perfectly matches the trajectory is formed on the ground, allowing surrounding vehicles to clearly identify the lane change direction of the vehicle.

[0103] As can be seen, in this embodiment, by acquiring driver body posture data, vehicle side offset rate relative to lane lines, and vehicle trajectory curvature, the target lane for lane changing and turning is comprehensively determined and the corresponding control point is identified. Based on the control point, a curve light carpet is generated and projected onto the ground. This not only accurately presents the light carpet expressing the vehicle's trajectory and lane-changing intention in the early stage before the vehicle begins to change lanes and has not yet invaded the adjacent lane, thus serving as a warning and filling the gap in existing technologies for such scenarios, but it can also adapt to various complex scenarios such as lane lines being fully available, partially missing, or completely unavailable. This effectively solves the problem of insufficient adaptability of existing vehicle light carpet solutions, while also addressing the safety warning issue of changing lanes at night without using turn signals, significantly improving the safety of nighttime driving and the accuracy of conveying lane-changing intentions.

[0104] Please see Figure 4 , Figure 4 This is a schematic diagram of a light carpet trajectory provided in an embodiment of this application, such as... Figure 4 As shown, a schematic diagram of generating a light carpet trajectory based solely on the Bézier curve algorithm is presented. It does not rely on actual road information such as lanes, lane lines, or vehicle trajectories. Based on the Bézier curve algorithm, a curved line (light carpet trajectory) that starts from the vehicle's current position (origin) and extends smoothly is generated solely through four preset target control points.

[0105] Specifically, the thin black polyline connecting multiple target control points forms the "coordinate skeleton" for Bézier curve calculation, clearly marking the coordinate reference from the vehicle's current position (origin) to the intermediate control point and then to the final control point; the black dashed line connecting multiple target control points is the dynamic traction auxiliary line, which intuitively presents the weighted traction relationship of the target control point on the curve. For example, the intermediate control point uses the traction of the dashed line to make the curve bend in its own direction, avoiding a harsh transition of the polyline; the thick black line connecting multiple target control points is the final generated light carpet trajectory, that is, the output result of the Bézier curve. It forms a natural and smooth curvature along the traction trend of the target control points, which is the actual shape of the light carpet projected onto the ground.

[0106] visible, Figure 4 The entire process of Bézier curve generation, from coordinate anchoring and dynamic traction to the creation of a smooth light carpet trajectory, is fully presented. This verifies the feasibility of the algorithm in generating a light carpet projection that meets the requirements with only a few control points, providing algorithmic support for subsequent adaptation to actual lane-changing scenarios.

[0107] Furthermore, combined Figure 4 Please see Figure 5 , Figure 6 and Figure 7 , Figure 5 This is a schematic diagram of a light carpet trajectory with the target lane being the current lane, provided in an embodiment of this application. Figure 6 This is a schematic diagram of the light carpet trajectory for a target lane that is the left-adjacent lane, provided in an embodiment of this application. Figure 7 This is a schematic diagram of a light carpet trajectory for a target lane that is the adjacent lane on the right, provided in an embodiment of this application. Figure 5 , Figure 6 and Figure 7 As shown, the light carpet trajectories are presented in three scenarios: the vehicle maintains a straight line, changes lanes to the left, and changes lanes to the right. These light carpet trajectories are all generated based on the Bézier curve algorithm and can adapt to complex scenarios such as complete, missing, or unavailable lane lines.

[0108] Specifically, Figure 5 In scenarios where the vehicle is traveling straight, all four target control points are located on the center line of the current lane. The positions of the first two control points perfectly match the vehicle's trajectory along the center line of the current lane (the two control points closest to the vehicle's current position are fixed on the vehicle's trajectory), while the positions of the latter two control points are located on the center line of the current lane (i.e., the target lane). The generated light carpet trajectory is a straight line, which can be stably output in scenarios where lane lines are complete, missing, or unavailable, providing the vehicle with clear visual guidance for lane centering and ensuring driving stability when traveling straight.

[0109] Specifically, Figure 6In the scenario of a vehicle changing lanes to the left, the first two control points are located on the center line of the current lane. This is because the vehicle's trajectory at the initial stage of the lane change still follows the center line of the current lane without any lateral deviation. The latter two control points fall on the center line of the target lane on the left. The generated light carpet trajectory is a smooth curve that bends to the left, which can project a warning at the initial stage of the lane change, before the vehicle enters the left lane, ensuring that the lane change intention is clearly conveyed.

[0110] Specifically, Figure 7 In the scenario of a vehicle changing lanes to the right, the first two control points are located on the center line of the current lane. This is because the vehicle's trajectory at the initial stage of the lane change still follows the center line of the current lane without any lateral deviation. The latter two control points fall on the center line of the target lane on the right. The generated light carpet trajectory is a smooth curve that bends to the right, which can project a warning at the initial stage of the lane change, before the vehicle enters the right lane, ensuring that the lane change intention is clearly conveyed.

[0111] As can be seen, in this embodiment, the light carpet trajectory is generated based on the Bézier curve algorithm for three scenarios: driving straight, changing lanes to the left, and changing lanes to the right. By matching the control point layout strategy of the vehicle's running trajectory and the center line of the target lane, it can adapt to complex scenarios such as lane lines being complete, missing, or unavailable. The driving intention can be clearly conveyed at the beginning of the lane change, effectively improving the safety of nighttime driving.

[0112] Please see Figure 8 , Figure 9 , Figure 8 This is a schematic diagram of a lighting scene for a vehicle traveling in the current lane, provided in an embodiment of this application. Figure 9 This is a schematic diagram of another lighting scenario for a vehicle traveling in the current lane, provided in an embodiment of this application. Figure 8 , Figure 9 As shown in the images, both figures illustrate the light carpet projection effect when a vehicle is traveling straight in its current lane without any intention to change lanes.

[0113] Specifically, Figure 8 This scenario corresponds to a vehicle traveling straight in its lane without intending to change lanes. In this case, the target lane is the current lane. According to the light carpet generation method for vehicle lane changing provided in this application, the system generates four target control points. The first two control points are anchored to the vehicle's current driving trajectory (along the center line of the current lane), while the latter two control points fall on the center line of the current lane. Based on these collinear control points, the Bezier curve algorithm generates a straight light carpet extending along the current lane (the color gradient area in front of the vehicle in the image). This light carpet maintains center alignment based on the lane line information identified by the perception module, and can also maintain stable output through the vehicle's trajectory when subsequent lane lines are missing, providing clear lane centering visual guidance for vehicles traveling straight in low-light nighttime scenarios.

[0114] Specifically, Figure 9This scenario corresponds to a vehicle traveling straight in its current lane without intending to change lanes. Both sides of the vehicle's lane markings have partial gaps, and the lane outlines shown as dashed lines in the image are automatically filled in by the system. Since the vehicle is actually close to the left lane marking of the current lane, the first two of the four target control points generated by the system are anchored to the vehicle's actual trajectory, positioned slightly to the left of the current lane, while the latter two are located on the center line of the current lane to anchor the overall lane direction. Based on this control point arrangement, the Bezier curve algorithm generates a light carpet that curves slightly to the left (the color gradient area in front of the vehicle in the image). This not only matches the vehicle's current trajectory but also returns to the lane center line through the traction of the latter two control points, ensuring that the light carpet remains within the current lane. This mechanism maintains lane baseline information through completion and dynamically adjusts the control points according to the vehicle's actual trajectory, ensuring the accuracy and continuity of the light carpet guidance.

[0115] Further, please refer to Figure 10 , Figure 10 This is another schematic diagram of a lighting scenario for a vehicle traveling in the current lane, provided in an embodiment of this application. Figure 10 As shown, this corresponds to a scenario where a vehicle is traveling straight at low speed on a road. To avoid unnecessary bending of the light carpet due to trajectory fluctuations in low-speed scenarios, a strategy of "defaulting to a straight light carpet at low speeds" is typically adopted. Even if there are partial gaps in the lane lines on both sides (the automatically completed lane lines are presented as dashed lines) or interference from other vehicles and pedestrians in the vicinity, the system still generates four collinear target control points. The first two anchor the vehicle's low-speed trajectory along the current lane, while the latter two fall on the center line of the current lane. A straight light carpet extending along the lane is generated using a Bezier curve algorithm (the color gradient area in front of the vehicle in the image), ensuring clear and stable visual guidance and improving safety during low-speed driving.

[0116] As can be seen, in this embodiment, for various scenarios where the vehicle is traveling straight in the current lane, the Bezier curve algorithm and dynamic control point arrangement strategy, combined with the optimization strategy of straightening the default light carpet in low-speed scenarios, can adapt to different states such as stable lane lines and partial availability, generate a light carpet that accurately fits driving needs, ensures clear and stable visual guidance, and effectively improves nighttime driving safety.

[0117] Please see Figure 11 , Figure 12 , Figure 11 This is a schematic diagram of a lighting scene for a vehicle changing lanes to the left, provided in an embodiment of this application. Figure 12 This is a schematic diagram of a lighting scene for a vehicle changing lanes to the right, provided in an embodiment of this application. Figure 11 , Figure 12 As shown, both images depict the light carpet projection effect when a vehicle is traveling in its current lane and intends to change lanes.

[0118] Specifically, Figure 11 In the scenario of a vehicle changing lanes to the left, the vehicle is currently traveling in its current lane with clear and complete lane lines, indicating a clear intention to change lanes to the left. According to the light carpet generation method for lane changing provided in this application, of the four target control points generated by the system, the first two are anchored to the vehicle's current trajectory, while the latter two fall on the center line of the left-hand target lane. Based on this arrangement, the Bezier curve algorithm generates a smoothly curved light carpet to the left (the color gradient area in front of the vehicle in the image). The light carpet is projected at the initial stage of the lane change, before the vehicle has fully entered the left-hand lane, clearly conveying the intention to change lanes to the left.

[0119] Specifically, Figure 12 In the scenario of a vehicle changing lanes to the right, the vehicle is currently traveling in its current lane with clear and intact lane markings, indicating a clear intention to change lanes to the right. The system generates four target control points, following a strategy where the first two are anchored to the current vehicle's trajectory, and the latter two fall on the center line of the target lane on the right. A smooth, right-curving light carpet (the color gradient area in front of the vehicle in the image) is generated using a Bezier curve algorithm. This light carpet can project a warning at the initial stage of a lane change, before the vehicle encroaches on the right lane, ensuring that the light carpet trajectory both matches the vehicle's trajectory and accurately points to the target lane on the right, thus guaranteeing clear transmission of the lane change intention and ensuring nighttime driving safety.

[0120] As can be seen, in this embodiment, for the scenario of vehicles changing lanes to the left or right, by using the Bezier curve algorithm and a precise control point layout strategy, a curved light carpet that conforms to the driving trajectory can be projected at the beginning of the lane change, clearly conveying the intention to change lanes. At the same time, it is suitable for complex nighttime scenarios where lane lines are available, effectively improving driving safety during lane changes.

[0121] Further, please refer to Figure 13 , Figure 13 This is a schematic diagram of a lighting scenario for vehicle driving when lane lines are unavailable, provided in an embodiment of this application. Figure 13 As shown, in a scenario where a vehicle is traveling on a road, there are no identifiable lane lines or clear lane divisions. According to the light carpet generation method for lane changing provided in this application, when lane lines are completely unavailable, the system no longer relies on lane references but generates the light carpet entirely based on the vehicle's own trajectory: all four target control points are anchored on the vehicle's trajectory and arranged along the trajectory's extension direction. Then, the Bezier curve algorithm generates a smoothly curved light carpet extending along the vehicle's trajectory (the color gradient area in front of the vehicle in the image). This provides the driver with a clear visual reference for the driving path without relying on lane lines, ensuring driving safety in nighttime scenarios without lane markings.

[0122] As can be seen, in this embodiment, in scenarios where lane lines are completely unavailable, a light carpet can be generated entirely based on the vehicle's own trajectory, independent of lane reference, to provide drivers with clear visual guidance for driving paths and effectively ensure driving safety in nighttime scenarios without lane markings.

[0123] This application embodiment can divide the electronic device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0124] Please see Figure 14 , Figure 14 This is a functional unit block diagram of a vehicle control system provided in this application embodiment. The vehicle control system 100 includes: an acquisition unit 101 and a processing unit 102; wherein, the acquisition unit 101 is used to acquire the driver's body posture data; the processing unit 102 is used to determine the first side offset rate and the second side offset rate of the vehicle based on the first lane line information of the lane where the vehicle is currently located, wherein the first side offset rate represents the rate at which the left side of the vehicle moves towards the left lane line of the lane where the vehicle is currently located, and the second side offset rate represents the rate at which the right side of the vehicle moves towards the right lane line of the lane where the vehicle is currently located; determine the vehicle's running trajectory and running trajectory curvature based on the vehicle's running status data; determine the target lane into which the vehicle is to change lanes based on the body posture data, the first side offset rate and the second side offset rate, and the running trajectory curvature; determine multiple target control points located on the target lane and the running trajectory; generate a light carpet trajectory based on the multiple target control points, and control the target headlights to project onto the ground according to the light carpet trajectory to form a curved light carpet.

[0125] In one possible embodiment, multiple target control points are determined on the target lane and the driving trajectory. The processing unit 102 is specifically configured to: determine a first light carpet guidance route within the target lane, the first light carpet guidance route including the lane centerline of the target lane; determine a first control point, a second control point, and a third control point and a fourth control point located on the driving trajectory, the first control point being located at the current position of the vehicle; and obtain the multiple target control points based on the first control point, the second control point, the third control point, and the fourth control point.

[0126] In one possible embodiment, a first control point and a second control point located on the running trajectory, and a third control point and a fourth control point located on the first light carpet guide route are determined. The processing unit 102 is specifically used to: determine the first coordinate of the first control point based on the current position of the vehicle, the first coordinate including a first horizontal coordinate and a first vertical coordinate, the axis direction corresponding to the vertical coordinate being the direction of a single lane extension, and the axis direction corresponding to the horizontal coordinate being parallel to the plane where the lane is located and perpendicular to the direction of the single lane extension; determine the second vertical coordinate of the second control point based on the first vertical coordinate and a first preset distance, and determine the coordinate point corresponding to the second vertical coordinate on the running trajectory as the second control point; determine the third vertical coordinate of the third control point based on the first vertical coordinate and the second preset distance, and determine the coordinate point corresponding to the third vertical coordinate on the first light carpet guide route as the third control point; determine the fourth vertical coordinate of the fourth control point based on the first vertical coordinate and the third preset distance, and determine the coordinate point corresponding to the fourth vertical coordinate on the first light carpet guide route as the fourth control point, wherein the values ​​of the first preset distance, the second preset distance, and the third preset distance increase sequentially.

[0127] In one possible embodiment, before determining the first light carpet guidance route within the target lane, the processing unit 102 is specifically configured to: determine the left and right lane lines of the target lane based on the second lane line information of the target lane, wherein the lane line information includes lane line position, lane line confidence, lane line stability, and lane line length; determine, based on the second lane line information, that the left and right lane lines of the target lane are in a fully usable state, or determine, based on the second lane line information, that the left and / or right lane lines of the target lane are in a partially usable state, wherein the partially usable state indicates that some lane lines are temporarily missing, and then fill in the partially missing lane lines based on the lane line status data corresponding to the left and / or right lane lines.

[0128] In one possible embodiment, the processing unit 102 is further configured to: determine that the left lane line and right lane line of the target lane are unavailable based on the second lane line information, and then determine a first control point, a second control point, a third control point and a fourth control point located on the running trajectory; and obtain the plurality of target control points based on the first control point, the second control point, the third control point and the fourth control point.

[0129] In one possible embodiment, the processing unit 102 determines the target lane the vehicle is to change lanes into based on the body posture data, the first vehicle side offset rate and the second vehicle side offset rate, and the curvature of the running trajectory. Specifically, the processing unit 102 is configured to: determine a first intended lane observed by the driver for lane changing based on the body posture data; determine a second intended lane for lane changing based on the first vehicle side offset rate and the second vehicle side offset rate; determine a third intended lane for lane changing based on the curvature of the running trajectory; if at least two of the first, second, and third intended lanes are adjacent lanes on the same direction side of the vehicle's current lane, then the adjacent lane on the same direction side is determined as the target lane the vehicle is to change lanes into, where the adjacent lane on the same direction side is either the left-side adjacent lane or the right-side adjacent lane; otherwise, the vehicle's current lane is determined as the target lane the vehicle is to change lanes into.

[0130] In one possible embodiment, the second intended lane into which the vehicle is to change lanes is determined based on the first vehicle side offset rate and the second vehicle side offset rate. The processing unit 102 is specifically configured to: if the first vehicle side offset rate is negative and the absolute value of the first vehicle side offset rate is greater than a preset rate, then determine the left adjacent lane of the vehicle's current lane as the second intended lane; if the second vehicle side offset rate is negative and the absolute value of the second vehicle side offset rate is greater than the preset rate, then determine the right adjacent lane of the vehicle's current lane as the second intended lane; otherwise, determine the vehicle's current lane as the second intended lane.

[0131] In one possible embodiment, the processing unit 102 determines a first vehicle side offset rate and a second vehicle side offset rate based on the first lane line information of the lane in which the vehicle is currently located. Specifically, the processing unit 102 is configured to: determine the left and right lane lines of the lane in which the vehicle is currently located based on the first lane line information; determine a first position on the left side of the vehicle and a second position on the right side of the vehicle based on the vehicle's current position and vehicle parameter information; calculate a first distance between the first position on the left side of the vehicle and the left lane line of the lane in which the vehicle is currently located at the current time point, and a second distance between the second position on the right side of the vehicle and the right lane line of the lane in which the vehicle is currently located at the current time point; calculate a third distance between the first position on the left side of the vehicle and the left lane line of the lane in which the vehicle is currently located at the previous time point, and a fourth distance between the second position on the right side of the vehicle and the right lane line of the lane in which the vehicle is currently located at the previous time point, wherein the time interval between adjacent time points is a preset time duration; obtain the first vehicle side offset rate based on the ratio of the difference between the first and third distances to the preset time duration; and obtain the second vehicle side offset rate based on the ratio of the difference between the second and fourth distances to the preset time duration.

[0132] In one possible embodiment, the processing unit 102 determines the vehicle's trajectory and trajectory curvature based on the vehicle's operating status data. Specifically, it is used to: determine the vehicle's driving position, steering angular rate, and steering wheel angle based on the vehicle's operating status data; determine the vehicle's driving trajectory based on the vehicle's driving position; calculate the first trajectory curvature based on the vehicle's steering angular rate; and calculate the second trajectory curvature based on the vehicle's steering wheel angle; and perform a weighted summation of the first trajectory curvature and the second trajectory curvature based on a first preset weight and a second preset weight to obtain the vehicle's trajectory curvature.

[0133] As can be seen, in this embodiment, by acquiring driver body posture data, vehicle side offset rate against lane lines, and vehicle trajectory curvature, the target lane to be changed and the corresponding control point is determined. Based on the control point, a curve light carpet is generated and projected onto the ground to accurately convey the vehicle's lane change intention. This effectively solves the safety warning problem of changing lanes at night without using turn signals, and improves the safety of nighttime driving and the accuracy of conveying lane change intention.

[0134] It is understood that since the method embodiments and the device embodiments are different presentations of the same technical concept, the content of the method embodiment section in this application should be adapted to the device embodiment section in a synchronous manner, and will not be repeated here.

[0135] Figure 15This is a structural block diagram of an electronic device provided in an embodiment of this application. For example... Figure 15 As shown, the electronic device 1500 may include one or more components: a processing module 1501 and a memory 1502 coupled to the processing module 1501, wherein the memory 1502 may store one or more computer programs, which may be configured to implement the methods described in the examples above when executed by one or more processing modules 1501. The electronic device 1500 may be as follows: Figure 1 The processor 110 shown.

[0136] Processing module 1501 may include one or more processing cores. Processing module 1501 connects to various parts within the electronic device 1500 using various interfaces and lines. It executes various functions and processes data of the electronic device 1500 by running or executing instructions, programs, code sets, or instruction sets stored in memory 1502, and by calling data stored in memory 1502. Optionally, processing module 1501 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processing module 1501 may integrate one or more of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. It is understood that the aforementioned modem may also not be integrated into processing module 1501 and may be implemented separately through a communication chip.

[0137] The memory 1502 may include random access memory (RAM) or read-only memory (ROM). The memory 1502 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1502 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the above-described method examples. The data storage area may also store data created during the use of the electronic device 1500.

[0138] It is understood that the electronic device 1500 may include more or fewer structural elements than those shown in the above block diagram, such as a power module, physical buttons, a WiFi (Wireless Fidelity) module, a speaker, a Bluetooth module, sensors, etc., without limitation.

[0139] This application also provides a computer storage medium storing a computer program / instructions thereon, which, when executed by a processor, implements some or all of the steps of any of the methods described in the above method embodiments.

[0140] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments.

[0141] It should be understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0142] In the several embodiments provided in this application, it should be understood that the disclosed methods, apparatuses, and systems can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for example, the division of units is merely a logical functional division, and there may be other division methods in actual implementation; 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 through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0143] 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.

[0144] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can be physically comprised separately, or two or more units can be integrated into one unit. The integrated unit described above can be implemented in hardware or in the form of hardware plus software functional units.

[0145] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute partial steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, volatile memory, or non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM), etc., which are various media capable of storing program code.

[0146] While the present invention has been disclosed above, it is not limited thereto. Any person skilled in the art can easily conceive of variations or substitutions without departing from the spirit and scope of the present invention, and various modifications and alterations can be made, including combinations of the different functions and implementation steps described above, as well as software and hardware implementation methods, all of which are within the protection scope of the present invention.

Claims

1. A method for generating a light blanket for vehicle lane changes, characterized in that, A processor for use in a vehicle control system, the vehicle control system further including a target vehicle light disposed at the front of the vehicle, the processor being connected to the target vehicle light, the method comprising: Acquire driver's body posture data; The first vehicle side offset rate and the second vehicle side offset rate are determined based on the first lane line information of the lane where the vehicle is currently located. The first vehicle side offset rate represents the rate at which the left side of the vehicle moves toward the left lane line of the lane where the vehicle is currently located, and the second vehicle side offset rate represents the rate at which the right side of the vehicle moves toward the right lane line of the lane where the vehicle is currently located. The vehicle's trajectory and trajectory curvature are determined based on the vehicle's operating status data; The target lane into which the vehicle is to change lanes is determined based on the body posture data, the first vehicle side offset rate and the second vehicle side offset rate, and the curvature of the running trajectory. Identify multiple target control points located on the target lane and the operating trajectory; A light carpet trajectory is generated based on the multiple target control points, and the target vehicle lights are controlled to project onto the ground according to the light carpet trajectory to form a curved light carpet.

2. The method according to claim 1, characterized in that, The determination of multiple target control points located on the target lane and the operating trajectory includes: Determine a first light carpet guidance route within the target lane, wherein the first light carpet guidance route includes the lane centerline of the target lane; Determine a first control point and a second control point located on the running trajectory, and a third control point and a fourth control point located on the first light carpet guidance route, wherein the first control point is located at the current position of the vehicle; The plurality of target control points are obtained based on the first control point, the second control point, the third control point, and the fourth control point.

3. The method according to claim 2, characterized in that, The determination of the first control point, the second control point located on the running trajectory, and the third control point and the fourth control point located on the first light carpet guidance route includes: The first coordinates of the first control point are determined based on the current position of the vehicle. The first coordinates include a first horizontal coordinate and a first vertical coordinate. The axial direction corresponding to the vertical coordinate is the direction of extension of a single lane, and the axial direction corresponding to the horizontal coordinate is parallel to the plane where the lane is located and perpendicular to the direction of extension of the single lane. The second ordinate of the second control point is determined based on the first ordinate and the first preset distance, and the coordinate point corresponding to the second ordinate on the running trajectory is determined as the second control point; The third ordinate of the third control point is determined based on the first ordinate and the second preset distance, and the coordinate point corresponding to the third ordinate on the first light carpet guide route is determined as the third control point; The fourth ordinate of the fourth control point is determined based on the first ordinate and the third preset distance, and the coordinate point corresponding to the fourth ordinate on the first light carpet guide route is determined as the fourth control point, with the values ​​of the first preset distance, the second preset distance and the third preset distance increasing sequentially.

4. The method according to claim 2 or 3, characterized in that, Before determining the first light blanket guidance route within the target lane, the method includes: The left and right lane lines of the target lane are determined based on the second lane line information of the target lane. The lane line information includes lane line position, lane line confidence, lane line stability, and lane line length. Based on the second lane line information, it is determined that the left and right lane lines of the target lane are in a fully usable state, or... Based on the second lane line information, it is determined that the left lane line and / or right lane line of the target lane are in a partially available state. The partially available state indicates that some lane lines are temporarily missing. Then, the partially missing lane lines are filled in according to the lane line status data corresponding to the left lane line and / or the right lane line.

5. The method according to claim 4, characterized in that, The method further includes: If the left and right lane lines of the target lane are determined to be unavailable based on the second lane line information, then the first control point, the second control point, the third control point, and the fourth control point located on the running trajectory are determined. The plurality of target control points are obtained based on the first control point, the second control point, the third control point, and the fourth control point.

6. The method according to claim 1, characterized in that, The step of determining the target lane that the vehicle is to change lanes into based on the body posture data, the first vehicle side offset rate and the second vehicle side offset rate, and the curvature of the running trajectory includes: The driver's first intended lane to enter is determined based on the body posture data. The second intended lane that the vehicle is to change lanes into is determined based on the first vehicle side offset rate and the second vehicle side offset rate. The third intended lane that the vehicle is to change lanes into is determined based on the curvature of the running trajectory. If at least two of the first intended lane, the second intended lane, and the third intended lane are adjacent lanes on the same direction side of the lane where the vehicle is currently located, then the adjacent lane on the same direction side is determined as the target lane into which the vehicle is to change lanes. The adjacent lane on the same direction side is either the left adjacent lane or the right adjacent lane. Otherwise, the lane in which the vehicle is currently located will be determined as the target lane into which the vehicle will change lanes.

7. The method according to claim 6, characterized in that, Determining the second intended lane that the vehicle is to change lanes into based on the first vehicle side offset rate and the second vehicle side offset rate includes: If the first vehicle side offset rate is negative and the absolute value of the first vehicle side offset rate is greater than the preset rate, then the left adjacent lane of the lane where the vehicle is currently located is determined as the second intended lane. If the second vehicle side offset rate is negative and the absolute value of the second vehicle side offset rate is greater than the preset rate, then the right adjacent lane of the lane where the vehicle is currently located is determined as the second intended lane. Otherwise, the lane where the vehicle is currently located will be designated as the second intended lane.

8. The method according to claim 6, characterized in that, Determining the first and second vehicle side offset rates of the vehicle based on the first lane line information of the lane the vehicle is currently in includes: The left and right lane lines of the lane where the vehicle is currently located are determined based on the first lane line information. The first position on the left side of the vehicle and the second position on the right side of the vehicle are determined based on the vehicle's current position and vehicle parameter information. Calculate the first distance between the first position of the vehicle's left side at the current time point and the left lane line of the lane the vehicle is currently in, and the second distance between the second position of the vehicle's right side and the right lane line of the lane the vehicle is currently in; and, Calculate the third distance between the first position of the left side of the vehicle at the previous time point and the left lane line of the lane the vehicle is currently in, and the fourth distance between the second position of the right side of the vehicle and the right lane line of the lane the vehicle is currently in. The time interval between adjacent time points is a preset time length. The first vehicle side offset rate is obtained based on the ratio between the difference between the first distance and the third distance and the preset interval duration; and, The second vehicle side offset rate is obtained by the ratio between the difference between the second distance and the fourth distance and the preset interval duration.

9. The method according to claim 8, characterized in that, Determining the vehicle's trajectory and trajectory curvature based on the vehicle's operating status data includes: The vehicle's driving position, steering angular rate, and steering wheel angle are determined based on the vehicle's operating status data. The vehicle's trajectory is determined based on its driving position. The first running trajectory curvature of the vehicle is calculated based on the vehicle's steering angular rate, and the second running trajectory curvature of the vehicle is calculated based on the vehicle's steering wheel angle. The curvature of the vehicle's trajectory is obtained by weighted summation of the first and second running trajectory curvatures according to the first and second preset weights.

10. A vehicle control system, characterized in that, The vehicle control system includes a processor and a target headlight disposed in front of the vehicle, the processor being connected to the target headlight, wherein the system is configured to perform the steps of the method as described in any one of claims 1-9.

Images