Staged lane departure suppression method, system and equipment and storage medium

Abstract

The invention relates to the technical field of automobiles, and particularly provides a staged lane departure suppression method, system and device and a storage medium, and the method comprises the steps: obtaining vehicle transverse state information containing a transverse offset in real time; the operation intention of a driver is recognized, and whether active lane changing or return steering actions exist or not is judged; judging whether an inhibition mode activation condition is met or not based on the transverse offset and the intention of the driver; after activation, the deviation severity level is determined according to the transverse offset, corresponding control strategies are selected according to the deviation severity level, and different strategies correspond to different priority configurations of transverse and course control; adjusting the combined control algorithm parameters based on the control phase and the target to generate an auxiliary steering instruction; and finally executing the instruction to suppress lane departure. Through cooperation of a staged control strategy and driver intention recognition, the safety, smoothness and man-machine co-driving coordination of the system are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of automobiles, and particularly relates to a staged lane departure inhibition method, system, device and storage medium. BACKGROUND

[0002] With the development of automobile intelligence, the lane departure inhibition system (LDP) has become a key technology for improving active safety. However, the existing systems generally have the problems of single intervention strategy and insufficient driver coordination. The traditional system usually performs fixed-intensity intervention when the vehicle approaches the lane boundary, and fails to dynamically adjust the control strategy according to the severity of the deviation, which easily leads to a jarring correction process or a "drawing a dragon" phenomenon. At the same time, the system often lacks accurate judgment of the real-time operation intention of the driver, and still forcibly intervenes when the driver actively changes lanes or corrects the direction, causing man-machine conflict and affecting the driving experience and system acceptance. Therefore, there is an urgent need for a solution that can intelligently identify driving intention and implement fine-grained hierarchical control according to the degree of deviation, ensuring safety while realizing harmonious co-driving of man and machine. SUMMARY

[0003] In view of the above problems of the prior art, the present application provides a staged lane departure inhibition method, system, device and storage medium to solve the above technical problems.

[0004] In a first aspect, the present application provides a staged lane departure inhibition method, comprising: obtaining real-time lateral state information of the vehicle, the lateral state information at least including a lateral offset; identifying the driver's operation intention, which includes judging whether the driver has an active lane change intention or an active right-turn action; judging whether the activation condition of the lane departure inhibition mode is met based on the lateral offset and the driver's operation intention; when the activation condition is met, determining the severity level of the vehicle's deviation according to the lateral offset, and selecting a corresponding control strategy based on the severity level of the deviation, wherein different control strategies correspond to different priority configurations of lateral control and heading control; adjusting the parameters of the combined control algorithm based on the determined control stage and control target to generate an auxiliary steering instruction, and executing the auxiliary steering instruction to inhibit lane departure.

[0005] In an optional embodiment, the real-time lateral state information of the vehicle is obtained, comprising: obtaining lane line information through an image sensor; obtaining vehicle speed and yaw rate information through a vehicle bus; Based on the lane line information and vehicle state information, a lateral offset and a heading angle of the vehicle are calculated.

[0006] In an optional embodiment, the driver operation intention is identified, including: If the steering wheel torque or the steering angle speed is monitored to exceed the intention threshold, and the lateral movement trend of the vehicle is consistent with the lane deviation direction, it is determined that there is an active lane change intention. If the steering wheel torque or the steering angle speed is monitored to exceed the intention threshold, and the lateral movement trend of the vehicle points to the center of the lane, it is determined that there is an active return steering action.

[0007] In an optional embodiment, based on the lateral offset and the driver operation intention, it is determined whether the activation condition of the lane deviation suppression mode is met, including: The absolute value of the real-time acquired lateral offset is compared with a dynamic first activation threshold, and the first activation threshold is determined based on the minimum value of the physical lane boundary and the expected driving area boundary of the driver habit; Only when the absolute value of the lateral offset is greater than the first activation threshold, and the lane change intention and the active return steering action are not identified, it is determined that the activation condition is met.

[0008] In an optional embodiment, the deviation severity level of the vehicle is determined according to the lateral offset; based on the deviation severity level, a corresponding control strategy is selected, including: The absolute value of the lateral offset is compared with a preset second threshold; When the absolute value of the lateral offset is greater than the second threshold, it is determined as a serious deviation level, and a first control strategy with a priority target of quickly reducing the lateral offset is selected; When the absolute value of the lateral offset is less than or equal to the second threshold, it is determined as a mild deviation level, and a second control strategy with a priority target of smoothly adjusting the heading of the vehicle is selected; The first control strategy includes: in the combined control algorithm, the weight of the first control amount based on the lateral offset error is increased, so that the system output is mainly aimed at the auxiliary steering instruction of quickly reducing the lateral offset; The second control strategy includes: in the combined control algorithm, the weight of the second control amount based on the heading angle error is increased, so that the system output is mainly aimed at the auxiliary steering instruction of smoothly adjusting the heading of the vehicle and stabilizing the return to the center of the lane.

[0009] In an optional embodiment, based on the determined control stage and control target, the parameters of the combined control algorithm are adjusted to generate the auxiliary steering instruction, including: The combination control algorithm adopts a double-PID control structure, including a first PID controller based on lateral offset error and a second PID controller based on heading angle error; The output of the first PID controller is a first control quantity The output of the second PID controller is a second control quantity ; The auxiliary steering instruction is a weighted sum of the first control quantity and the second control quantity , that is , wherein and are weight coefficients; When in the first control stage, the weight coefficients are adjusted to , so as to increase the proportion of the first control quantity in the final auxiliary steering instruction; When in the second control stage, the weight coefficients are adjusted to , so as to increase the proportion of the second control quantity in the final auxiliary steering instruction.

[0010] In an optional embodiment, the method further comprises: The calculation method of the first control quantity comprises:

[0011]

[0012] wherein, is a lateral offset, which refers to the lateral distance from the current position of the vehicle to the center line of the lane; is a lateral offset error, which is the input of the PID controller; is a set target value; is an expected steering wheel angle based on the lateral offset, which is the output of the lateral offset PID controller, and the purpose is to eliminate the lateral offset error and control the vehicle back to the center line of the lane; , and are the proportional, integral and differential coefficients of the PID controller; The calculation method of the second control quantity comprises:

[0013]

[0014] is a heading angle deviation; is the input of the PID controller; is a target value of the heading angle; is the desired steering wheel angle based on the heading angle error; , and are the proportional, integral, and derivative coefficients of the PID controller.

[0015] In a second aspect, the present application provides a staged lane departure mitigation system, comprising: an information acquisition module configured to acquire real-time lateral state information of the vehicle, the lateral state information comprising at least a lateral offset; an intention recognition module configured to recognize a driver operation intention, the recognizing a driver operation intention comprising: judging whether the driver has an active lane change intention or an active straightening action; a departure judgment module configured to judge whether an activation condition of a lane departure mitigation mode is satisfied based on the lateral offset and the driver operation intention; a strategy selection module configured to, when the activation condition is satisfied, determine a departure severity level of the vehicle according to the lateral offset, and select a corresponding control strategy based on the departure severity level, wherein different control strategies correspond to different priority configurations of lateral control and heading control; an instruction generation module configured to adjust parameters of a combined control algorithm based on the determined control stage and control target, to generate an auxiliary steering instruction, and execute the auxiliary steering instruction to mitigate lane departure.

[0016] In a third aspect, a device is provided, comprising: a memory configured to store a staged lane departure mitigation program; a processor configured to implement steps of the staged lane departure mitigation method provided in the first aspect when executing the staged lane departure mitigation program.

[0017] In a fourth aspect, a computer readable storage medium is provided, the storage medium storing a staged lane departure mitigation program, the staged lane departure mitigation program being configured to implement steps of the staged lane departure mitigation method provided in the first aspect when executed by a processor.

[0018] The beneficial effects of the present application are that the staged lane departure suppression method, system, device and storage medium provided by the present application significantly improve the comprehensive performance of the lane departure suppression system by introducing a staged control strategy and a driver intention recognition mechanism. The beneficial effects mainly include: the system can intelligently divide the control stage according to the lateral offset, quickly corrects the deviation in the early stage to ensure safety, and prioritizes the stability in the return stage to improve comfort, effectively avoiding the "drawn dragon" phenomenon; through dynamic identification of the driver's steering intention, human-machine collaborative control is realized, which not only ensures effective suppression of unintended deviation, but also avoids conflicts with the driver's active operation, greatly improving the system acceptance; the double-PID weighted control structure is adopted, and the smooth transition between different control targets is realized through parameter adaptive adjustment, making the auxiliary intervention process more accurate and natural. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative labor.

[0020] Figure 1 is a schematic flow chart of the method of an embodiment of the present application.

[0021] Figure 2 is a schematic principle diagram of the method of an embodiment of the present application.

[0022] Figure 3 is a schematic flow chart of the strategy selection of the method of an embodiment of the present application.

[0023] Figure 4 is a schematic block diagram of the system of an embodiment of the present application.

[0024] Figure 5 is a structural schematic diagram of a device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor should be within the scope of protection of the present application.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description herein is for describing particular embodiments only and is not intended to be limiting of the application.

[0027] The method for stage-based lane departure suppression provided by the embodiments of the application is executed by a computer device, and accordingly, a stage-based lane departure suppression system runs in the computer device.

[0028] Figure 1 is a schematic flowchart of the method of an embodiment of the application. In this flowchart, Figure 1 The execution subject can be a stage-based lane departure suppression system. The order of the steps in the flowchart can be changed according to different requirements, and some steps can be omitted.

[0029] As Figure 1 shown, the method comprises: S1. Real-time acquisition of lateral state information of the vehicle, the lateral state information comprising at least a lateral offset; S2. Identification of the driver's operation intention; the identification of the driver's operation intention comprising: judging whether the driver has an active lane change intention or an active straightening steering action; S3. Based on the lateral offset and the driver's operation intention, judging whether an activation condition of a lane departure suppression mode is met; S4. When the activation condition is met, determining a departure severity level of the vehicle according to the lateral offset; based on the departure severity level, selecting a corresponding control strategy, wherein different control strategies correspond to different priority configurations of lateral control and heading control; S5. Based on the determined control stage and control target, adjusting parameters of a combined control algorithm to generate an auxiliary steering instruction; executing the auxiliary steering instruction to suppress lane departure.

[0030] Please refer to Figure 2 for a detailed description of the application.

[0031] In an embodiment of the application, based on step S1, a possible embodiment will be given below to non-restrictively describe the specific implementation thereof.

[0032] First, a front road image is collected in real time by an image sensor (such as a monocular camera) deployed at the rear side of the front windshield of the vehicle. By using an image processing unit built-in, a lane line detection algorithm based on Hough transform or convolutional neural network is used to process the image to identify left and right lane lines, and a mathematical model (usually a quadratic curve) of the current lane is fitted. Based on this model, the lateral position of the vehicle relative to the lane center line can be calculated.

[0033] Meanwhile, vehicle state data provided by the vehicle controller, inertial measurement unit (IMU) and wheel speed sensor are acquired through the vehicle CAN bus, including but not limited to vehicle speed v and yaw rate γ.

[0034] Finally, the data fusion module comprehensively processes the received lane line information and vehicle state information: lateral offset is directly obtained by calculating the perpendicular distance between the current position of the vehicle and the lane center line; and heading angle is obtained by fusion calculation, specifically, the included angle between the actual heading angle of the vehicle and the tangent direction of the lane, which can be estimated in combination with the lane curvature, vehicle speed v and yaw rate γ, for example, by integrating the yaw rate and supplemented by the visual observation value of the lane line direction for correction to ensure the accuracy and real-time performance of the data.

[0035] In an embodiment of the present application, based on step S2, a possible embodiment will be given below to non-limitingly illustrate the specific implementation thereof.

[0036] Hardware signal acquisition: the system acquires the steering wheel torque T d applied by the driver in real time through the torque sensor installed on the steering column, and acquires the steering wheel angular velocity ω through the angular sensor. Meanwhile, the lateral acceleration a y and the yaw rate γ provided by the inertial measurement unit (IMU) are acquired through the vehicle CAN bus.

[0037] Driver active intervention recognition logic: set an intention threshold T threshold and ω threshold . When the steering wheel torque ∣T d ∣>T threshold or the steering wheel angular velocity ∣ω∣>ω threshold is monitored, it is determined that the driver has clear active steering intervention.

[0038] Motion trend and intention discrimination: active lane change intention determination: on the basis of detecting the active steering intervention of the driver, the system further analyzes the motion trend of the vehicle. The current lateral speed v y of the vehicle (which can be obtained by integrating the lateral acceleration a y and combining other state observers) and the lateral displacement trend are calculated. If the direction of the lateral speed v y is consistent with the direction of the current lane deviation (for example, the vehicle is deviating to the right of the lane, and the deviation direction is right), it is determined that the driver intends to actively change lanes, and the system should avoid activating or should exit the lane deviation suppression.

[0039] Active correction steering action determination: also based on the detection of the driver's active steering intervention, if the direction of the lateral velocity v y points to the lane center line (i.e. opposite to the current deviation direction), it is determined that the driver is actively correcting the vehicle back to the lane center, and the system should also suppress its own intervention behavior and return the control to the driver.

[0040] To improve the robustness of the judgment, a time window (such as 100ms) can be introduced to perform short-time integration or filtering processing on the above signals to avoid misjudgment caused by signal noise.

[0041] In an embodiment of the present application, based on step S3, a possible embodiment will be given below to specifically describe the non-limiting embodiment.

[0042] S301. Calculation of dynamic first activation threshold The system continuously obtains the physical lane boundary information through the front-view camera to determine the actual distances L left and L right of the vehicle from the left and right lane lines. At the same time, the system establishes the expected driving area boundary E left and E right based on the historical driving data of the driver (such as the average lateral position in the past 5 minutes). The final dynamic first activation threshold e y1_dynamic is determined by the following formula:

[0043] Where α and β are safety factors (usually α = 0.8, β = 0.9) to ensure that the system is activated in time when the vehicle approaches the physical boundary or deviates significantly from the driving habit area.

[0044] S302. Multi-condition cooperative judgment mechanism The system maintains a state machine, which performs the following judgment process at each control period (such as 10ms): Read the current lateral offset e y and the calculated e y1_dynamic .

[0045] Obtain the flag (Flag lanechange and Flag return ) output by the driver intention recognition module.

[0046] Activate the LDP mode only when the following three conditions are met simultaneously:

[0047] (No lane change intention is recognized) No active response detected S303. Anti-interference processing To avoid false activation caused by instantaneous fluctuation, a 100ms confirmation window is set. Only when the above conditions are continuously met for more than the confirmation window length, it is finally determined as valid activation. At the same time, when any condition is not met, the activation state is immediately exited to ensure the principle of driver priority.

[0048] In an embodiment of the present application, based on step S4, a possible embodiment will be given below to non-restrictively illustrate the specific implementation thereof.

[0049] The system presets a second threshold e y2 = 0.5m. In each control cycle (10ms), the absolute value of the real-time calculated lateral deviation is compared with the threshold: When , it is determined as a serious deviation level, and enters the first stage control, and the first stage corresponds to the first control strategy; When , it is determined as a mild deviation level, and enters the second stage control, and the second stage corresponds to the second control strategy.

[0050] The first control strategy includes: in the combined control algorithm, increasing the weight of the first control amount based on the lateral deviation error, so that the system output is mainly aimed at the auxiliary steering instruction for quickly reducing the lateral deviation; The second control strategy includes: in the combined control algorithm, increasing the weight of the second control amount based on the heading angle error, so that the system output is mainly aimed at the auxiliary steering instruction for smoothly adjusting the vehicle heading and stabilizing the regression of the lane center.

[0051] In an embodiment of the present application, based on step S5, a possible embodiment will be given below to non-restrictively illustrate the specific implementation thereof, with reference to Figure 3 .

[0052] After the system is powered on, the double-PID controller parameters are initialized: Lateral deviation PID parameters: = 2.5, = 0.1, = 0.05; Heading angle PID parameters: = 1.8, = 0.08, = 0.03; Initial weight coefficient: = 0.5, = 0.5; Target value setting: = 0, =0.

[0053] Get the current lateral offset and the heading angle Then, calculate the instantaneous error: Lateral offset error:

[0054] Heading angle error:

[0055] The combined control algorithm adopts a double-PID control structure, including a first PID controller based on the lateral offset error and a second PID controller based on the heading angle error.

[0056] Lateral offset PID: with the lateral offset error as input, its goal is to control the lateral position of the vehicle within the desired range (e.g. the center of the lane). The output of this PID can be interpreted as the desired steering angle based on the lateral position. The calculation method of the first control quantity includes:

[0057] where, is the lateral offset, which refers to the lateral distance from the current position of the vehicle to the center line of the lane; is the lateral offset error, which is the input of the PID controller; is the set target value; is the desired steering angle based on the lateral offset, which is the output of the lateral offset PID controller, aiming to eliminate the lateral offset error and control the vehicle back to the center of the lane; , and are the proportional, integral, and derivative coefficients of the PID controller.

[0058] Heading angle PID: with the heading angle error as input, its goal is to make the actual heading angle of the vehicle follow the desired heading angle and make the vehicle return to the correct direction. The output of this PID is the desired steering angle based on the heading angle. The calculation method of the second control quantity includes:

[0059] is the heading angle deviation; is the input of the PID controller; is the target value of the heading angle; is the desired steering angle based on the heading angle error; , and are the proportional, integral, and derivative coefficients of the PID controller.

[0060] The output of the first PID controller is the first control quantity , the output of the second PID controller is the second control variable ; the auxiliary steering instruction is a weighted sum of the first control variable and the second control variable , i.e. , where and are weight coefficients; When in the first control phase, the weight coefficients are adjusted so as to increase the proportion of the first control variable in the final auxiliary steering instruction; When in the second control phase, the weight coefficients are adjusted so as to increase the proportion of the second control variable in the final auxiliary steering instruction. During system operation, the adjustment of the weight coefficients is dynamically performed according to the control phase in which the vehicle is located. When the system determines that the vehicle is in the first phase (emergency correction), the weight coefficient of the lateral deviation control is set to 0.8, and the weight coefficient

[0061] of the heading angle control is set to 0.2. Such weight distribution makes the control variable based on the lateral deviation error dominant in the auxiliary steering instruction output by the system, thereby ensuring that the system can quickly and effectively reduce the lateral deviation and timely correct the dangerous deviation state of the vehicle. When the deviation of the vehicle is preliminarily controlled, the system enters the second phase (smooth return), and the weight coefficient configuration is significantly changed. At this time, the system adjusts the weight coefficient to 0.3,

[0062] to 0.7. This adjustment greatly increases the proportion of the heading angle control variable in the combined instruction, and changes the control focus of the system from rapid correction to fine adjustment of the vehicle heading angle, ensuring that the vehicle returns to the center of the lane in a smooth and comfortable manner, effectively avoiding the "dragon drawing" phenomenon of the vehicle swinging back and forth during the return process. To prevent the integral term of the PID controller from accumulating indefinitely in the case of continuous error, causing the control instruction to abnormally increase, the system sets an anti-integral saturation mechanism. Specifically, the output of the integral term of the lateral deviation PID controller is limited to an amplitude range of ±50°, and the output of the integral term of the heading angle PID controller is limited to an amplitude range of ±30°. When the calculated value of the integral term of either party exceeds the corresponding limit, the system will automatically constrain it within the boundary value, thereby ensuring the stability and safety of the control system.

[0063] To prevent the integral term of the PID controller from accumulating indefinitely in the case of continuous error, causing the control instruction to abnormally increase, the system sets an anti-integral saturation mechanism. Specifically, the output of the integral term of the lateral deviation PID controller is limited to an amplitude range of ±50°, and the output of the integral term of the heading angle PID controller is limited to an amplitude range of ±30°. When the calculated value of the integral term of either party exceeds the corresponding limit, the system will automatically constrain it within the boundary value, thereby ensuring the stability and safety of the control system.

[0064] ​To further improve the driving experience, the system also performs output smoothing processing on the finally generated steering assistance instruction A first-order low-pass filter algorithm is used to filter the control instruction with a cutoff frequency of 10 Hz. This processing can effectively filter out the high-frequency mutation components in the instruction, making the control instruction output to the steering actuator more smooth and continuous, avoiding sudden and harsh rotation of the steering wheel, and significantly improving the smoothness and driving comfort of the system.

[0065] In some embodiments, the staged lane departure suppression system can include a plurality of functional modules composed of computer program segments. The computer programs of each program segment in the staged lane departure suppression system can be stored in the memory of the computer device and executed by at least one processor to perform the functions of staged lane departure suppression (see Figure 1 Description).

[0066] In this embodiment, the staged lane departure suppression system can be divided into a plurality of functional modules according to the functions it performs, as shown in Figure 4 The module referred to by the present application refers to a series of computer program segments that can be executed by at least one processor and can complete a fixed function, which are stored in the memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0067] An information acquisition module for acquiring the lateral state information of the vehicle in real time, the lateral state information including at least a lateral offset; An intention recognition module for recognizing the driver's operation intention, the recognizing the driver's operation intention including: judging whether the driver has an active lane change intention or an active straightening action; A departure judgment module for judging whether the activation condition of the lane departure suppression mode is met based on the lateral offset and the driver's operation intention; A strategy selection module for determining the departure severity level of the vehicle according to the lateral offset when the activation condition is met; selecting a corresponding control strategy based on the departure severity level, wherein different control strategies correspond to different priority configurations of lateral control and heading control; An instruction generation module for adjusting the parameters of the combined control algorithm based on the determined control stage and its control target to generate an auxiliary steering instruction; executing the auxiliary steering instruction to suppress lane departure.

[0068] Figure 5The device to which the stage-based lane departure suppression method provided by the embodiments of the present application can be applied. Those skilled in the art can understand that the device structure involved in the embodiments of the present application does not constitute a limitation on the device, and the device can include more or fewer components than shown, or combine certain components, or different component arrangements. In the embodiments of the present application, the device includes, but is not limited to, a laptop computer, a desktop computer, a workstation, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The device can also represent various forms of mobile devices, such as a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are merely examples, and are not intended to limit the implementation of the embodiments of the present application described herein and / or claimed.

[0069] The device 500 can include a processor 510, a memory 520, and a communication unit 530. These components communicate over one or more buses, and those skilled in the art can understand that the structure of the server shown in the figure does not constitute a limitation on the present application, and it can be a bus structure or a star structure, and can include more or fewer components than shown, or combine certain components, or different component arrangements.

[0070] The memory 520 can be used to store execution instructions for the processor 510, and the memory 520 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 520 are executed by the processor 510, the device 500 is enabled to perform some or all of the steps in the following method embodiments.

[0071] The processor 510 is the control center of the storage device, connects various parts of the entire electronic device through various interfaces and lines, and performs various functions of the electronic device and / or processes data by running or executing software programs and / or modules stored in the memory 520 and calling data stored in the memory. The processor can be composed of integrated circuits (ICs), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs connected together. For example, the processor 510 can only include a central processing unit (CPU). In the embodiments of the present application, the CPU can be a single operation core or can include multiple operation cores.

[0072] The communication unit 530 is configured to establish a communication channel, so that the storage device can communicate with other devices. The communication unit 530 is configured to receive user data sent by other devices or send user data to other devices.

[0073] The present application also provides a computer storage medium, wherein the computer storage medium can store a program, and the program can include some or all steps in the embodiments provided by the present application when executed. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM) and the like.

[0074] Those skilled in the art can clearly understand that the technology in the embodiments of the present application can be realized by means of software and necessary general hardware platforms. Based on such understanding, the technical solutions in the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and the like, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a second device, a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application.

[0075] In the present specification, the same or similar parts among various embodiments can be referred to each other. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0076] In the several embodiments provided by the present application, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. In actual implementation, another division manner can be used. For example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the systems or modules shown or discussed can be indirect coupling or communication connection through some interfaces. The coupling or communication connection can be electrical, mechanical or in other forms.

[0077] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed to multiple network modules. Part or all of the modules can be selected as needed to achieve the purpose of the embodiment.

[0078] In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0079] Although the present application has been described in detail through reference to preferred embodiments, it should be understood that the present application is not limited to the preferred embodiments. Various equivalents or alternatives to those preferred embodiments described herein can be made by those skilled in the art without departing from the spirit and scope of the present application. Any modifications or replacements of the embodiments of the present application should be within the scope of the present application.

Claims

1. A staged lane departure mitigation method characterized by, The method comprises: acquiring lateral state information of the vehicle in real time, the lateral state information comprising at least lateral offset; identifying driver operation intention; the identifying driver operation intention comprises: judging whether the driver has an active lane change intention or an active straightening steering action; judging whether an activation condition of a lane departure inhibition mode is met based on the lateral offset and the driver operation intention; when the activation condition is met, determining a departure severity level of the vehicle according to the lateral offset; and selecting a corresponding control strategy based on the departure severity level, wherein different control strategies correspond to different priority configurations of lateral control and heading control; adjusting parameters of a combined control algorithm based on the determined control stage and control target to generate an auxiliary steering instruction; and executing the auxiliary steering instruction to inhibit lane departure.

2. The method of claim 1, wherein, The method comprises: acquiring lane line information through an image sensor; acquiring vehicle speed and yaw rate information through a vehicle bus; calculating a lateral offset and a heading angle of the vehicle based on the lane line information and vehicle state information.

3. The method of claim 1, wherein, The method comprises: if the steering wheel torque or steering angle speed monitored exceeds an intention threshold value, and the lateral motion trend of the vehicle is consistent with the lane departure direction, it is determined that there is an active lane change intention; if the steering wheel torque or steering angle speed monitored exceeds an intention threshold value, and the lateral motion trend of the vehicle points to the lane center, it is determined that there is an active straightening steering action.

4. The method of claim 1, wherein, The method comprises: comparing the absolute value of the real-time acquired lateral offset with a dynamic first activation threshold value, the first activation threshold value being a minimum value determined based on a physical lane boundary and an expected driving area boundary of the driver's habit; only when the absolute value of the lateral offset is greater than the first activation threshold value, and no lane change intention or active straightening steering action is identified, it is determined that the activation condition is met.

5. The method of claim 1, wherein, determining a departure severity level of the vehicle according to the lateral offset; selecting a corresponding control strategy based on the departure severity level, comprising: comparing the absolute value of the lateral offset with a preset second threshold value; when the absolute value of the lateral offset is greater than the second threshold value, determining a severe departure level, and selecting a first control strategy with a priority target of rapidly reducing the lateral offset; when the absolute value of the lateral offset is less than or equal to the second threshold value, determining a mild departure level, and selecting a second control strategy with a priority target of smoothly adjusting the heading of the vehicle; the first control strategy comprises: in the combined control algorithm, increasing the weight of a first control amount based on the lateral offset error, so that the system output is an auxiliary steering instruction with a main target of rapidly reducing the lateral offset; the second control strategy comprises: in the combined control algorithm, increasing the weight of a second control amount based on the heading angle error, so that the system output is an auxiliary steering instruction with a main target of smoothly adjusting the heading of the vehicle and stabilizing the regression to the lane center.

6. The method of claim 1, wherein, based on the determined control phase and its control target, adjusting parameters of the combined control algorithm to generate an auxiliary steering instruction, comprising: the combined control algorithm adopts a double-PID control structure, including a first PID controller based on lateral offset error and a second PID controller based on heading angle error; an output of the first PID controller is a first control variable an output of the second PID controller is a second control variable ​ the auxiliary steering instruction is a weighted sum of the first control quantity and the second control quantity , i.e. wherein and are weight coefficients; when in said first control phase, adjusting said weight coefficient so as to increase said first control quantity in order to increase the proportion of said final auxiliary steering command in the final auxiliary steering command; When in the second control phase, adjust the weighting coefficients so that To increase the second control quantity The proportion of the final assisted steering command.

7. The method of claim 1, wherein, the method further comprises: the calculation method of the first control quantity comprises: wherein, is the lateral offset, which is the lateral distance from the current position of the vehicle to the center line of the lane; is the lateral offset error, which is the input of the PID controller; is the set target value; is the desired steering wheel angle based on the lateral offset, which is the output of the lateral offset PID controller, and the purpose is to eliminate the lateral offset error and control the vehicle back to the center line of the lane; , and are the proportional, integral, and derivative coefficients of the PID controller; the calculation method of the second control quantity comprises: is a heading angle deviation; is an input to the PID controller; is a target value of the heading angle; is a desired steering wheel angle based on the heading angle error; , and are proportional, integral, and derivative coefficients of the PID controller.

8. A staged lane departure mitigation system characterized by, comprising: an information acquisition module for acquiring real-time lateral state information of the vehicle, the lateral state information at least including lateral offset amount; an intention recognition module for recognizing driver operation intention; the recognition of the driver operation intention comprises: judging whether the driver has an active lane change intention or an active return-to-straight steering action; a deviation judgment module for judging whether an activation condition of a lane deviation suppression mode is met based on the lateral offset amount and the driver operation intention; a strategy selection module for determining a deviation severity level of the vehicle according to the lateral offset amount when the activation condition is met; selecting a corresponding control strategy based on the deviation severity level, wherein different control strategies correspond to different priority configurations of lateral control and heading control; an instruction generation module for adjusting parameters of the combined control algorithm based on the determined control phase and its control target to generate an auxiliary steering instruction; executing the auxiliary steering instruction to suppress lane deviation.

9. A staged lane departure mitigation apparatus characterized by, comprising: a memory for storing a staged lane deviation suppression program; a processor for implementing the steps of the staged lane deviation suppression method according to any one of claims 1-7 when executing the staged lane deviation suppression program.

10. A computer readable storage medium storing a computer program, characterized in that, the readable storage medium has a staged lane deviation suppression program stored thereon, and the staged lane deviation suppression program implements the steps of the staged lane deviation suppression method according to any one of claims 1-7 when executed by a processor.

Images