Lane keeping deviation correction method, system and equipment based on intention recognition and medium

By real-time monitoring and analysis of driver behavior, steering wheel status and vehicle driving information, the driver's lane change intention is determined, and the lane keeping system status is updated, the problem of lane keeping system competing with drivers in the existing technology is solved, and driving is improved Security and user experience.

CN119078825APending Publication Date: 2024-12-06ZHEJIANG SMART INTELLIGENCE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411376227.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-30
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing lane keeping assist system is prone to compete with the driver for the steering wheel when the driver actively deviates from the lane, resulting in poor driving safety and user experience.

Method used

By obtaining the driver's behavior information, steering wheel contact status information and vehicle driving information within the preset sampling time, the attitude tracking algorithm is used to determine the driver's lane change intention, and the lane keeping system is updated in combination with the steering wheel contact status and driving direction. state, avoid unnecessary intervention.

Benefits of technology

It improves driving experience and driving safety, ensures that the driver avoids automatic intervention of the lane keeping system when changing lanes independently, and improves the applicability of the system and user satisfaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119078825A_ABST
    Figure CN119078825A_ABST
Patent Text Reader

Abstract

The invention relates to a lane keeping deviation correction method, system and device based on intention recognition and a medium. The method comprises the following steps: acquiring the state of a lane keeping system, behavior information of a driver, contact state information of a steering wheel and driving information of a vehicle within a preset sampling duration; based on a posture tracking algorithm, determining the sight line direction of the driver according to the behavior information, and determining the lane changing intention of the driver based on the sight line direction; determining a steering wheel contact state based on the steering wheel contact state information; determining the driving direction of the vehicle based on the driving information; and updating the state of the lane keeping system based on the lane changing intention, the driving direction of the vehicle and the steering wheel contact state. According to the invention, the condition that the lane keeping system is automatically activated to carry out unnecessary intervention when the driver autonomously changes the lane is improved, and the driving experience and the driving safety of the user are greatly improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a lane keeping correction method, system, device and medium based on intention recognition. Background Art

[0002] With the rapid development of automotive electronic technology, lane keeping systems (Lane Keeping Assistance, LKA) are gradually being applied to vehicles. The lane keeping assist system monitors the relative position of the lane line and the vehicle in real time through cameras and sensors. When it detects that the vehicle has unintentionally deviated from the lane, the system will automatically intervene in the steering wheel to correct it so that the vehicle remains in the lane. However, the current lane keeping assist system will actively correct the driver regardless of whether the driver has actively deviated from the lane. As a result, when the driver has the intention to actively deviate from the lane, the lane keeping assist system will compete with the driver for the steering wheel, seriously affecting driving safety and user experience. Therefore, it is necessary to provide a lane keeping correction method, system, device and medium based on intention recognition. Summary of the invention

[0003] In view of the shortcomings of the prior art described above, an object of the present invention is to provide a lane keeping correction method, system, device and medium based on intention recognition, which improves the problem that the lane keeping system in the prior art is prone to poor driving safety.

[0004] To achieve the above-mentioned purpose and other related purposes, the present invention provides a lane keeping correction method based on intention recognition, comprising: obtaining the status of a lane keeping system, the driver's behavior information, the steering wheel contact status information and the vehicle's driving information within a preset sampling period; based on a posture tracking algorithm, determining the driver's line of sight direction according to the behavior information, and determining the driver's lane changing intention based on the line of sight direction; determining the steering wheel contact status based on the steering wheel contact status information; determining the vehicle's driving direction based on the driving information; and updating the status of the lane keeping system based on the lane changing intention, the vehicle's driving direction and the steering wheel contact status.

[0005] In one embodiment of the present invention, the posture tracking algorithm is based on the behavior information to determine the driver's line of sight direction, and based on the line of sight direction to determine the driver's intention to change lanes, including: based on the identification of the behavior information, judging the category of the behavior information: if the behavior information is eye movement information, then based on the eye posture tracking method, determining the driver's line of sight direction according to the behavior information; wherein the line of sight direction includes a first perspective, a second perspective and a third perspective with increasing angles; if the behavior information sequence is head information, then based on the head posture tracking method, determining the driver's line of sight direction according to the behavior information; based on the line of sight direction, determining the intention to change lanes.

[0006] In one embodiment of the present invention, determining the lane changing intention based on the line of sight direction includes: counting the number of times the line of sight direction switches from the second perspective to the first perspective, and the number of times the line of sight switches from the second perspective to the third perspective within the sampling duration; determining whether the number of times the line of sight direction switches from the second perspective to the first perspective / from the second perspective to the third perspective within the sampling duration is greater than a preset number threshold: if so, taking the corresponding first perspective / third perspective as the lane changing intention; otherwise, continuing to determine the driver's line of sight direction based on the behavior information within the next sampling duration.

[0007] In one embodiment of the present invention, determining the steering wheel holding state based on the steering wheel contact state information includes: judging whether the steering wheel contact state information is greater than or equal to a preset contact state threshold: if so, the steering wheel is in a holding state; otherwise, the steering wheel is in a non-holding state.

[0008] In one embodiment of the present invention, determining the driving direction of the vehicle based on the driving information includes: for the steering wheel hand torque in the driving information: judging whether the steering wheel hand torque is greater than or equal to a preset first threshold: if so, marking the steering wheel hand torque as a first steering wheel hand torque; otherwise, judging whether the steering wheel hand torque is less than or equal to a preset second threshold: if so, marking the steering wheel hand torque as a second steering wheel hand torque; otherwise, continuing to judge the next steering wheel hand torque; counting the total amount of the first steering wheel hand torque and the total amount of the second steering wheel hand torque; determining the driving direction of the vehicle based on the total amount of the first steering wheel hand torque and the total amount of the second steering wheel hand torque.

[0009] In one embodiment of the present invention, determining the driving direction of the vehicle based on the total amount of the first steering wheel hand torque and the total amount of the second steering wheel hand torque includes: judging whether the total amount of the first steering wheel hand torque is greater than or equal to a preset first total amount threshold value: if so, determining the driving direction as changing lanes in the first direction; otherwise, judging whether the total amount of the second steering wheel hand torque is greater than or equal to a preset second total amount threshold value: if so, determining the driving direction as changing lanes in the second direction; wherein the first direction is opposite to the second direction; otherwise, determining the driving direction as going straight.

[0010] In one embodiment of the present invention, the state of the lane keeping system is updated based on the lane changing intention, the driving direction of the vehicle and the steering wheel contact state, including: if the lane changing intention is the same as the driving direction and the steering wheel is in a held state, then the lane keeping system is kept in a disabled state; if the lane changing intention is different from the driving direction and / or the steering wheel is in a non-held state, then the lane keeping system is activated.

[0011] In one embodiment of the present invention, a lane keeping correction system based on intention recognition is also provided, and the system includes: a data acquisition module, which is used to obtain the status of the lane keeping system, the driver's behavior information, the steering wheel contact status information and the vehicle's driving information within a preset sampling period; a driver behavior recognition module, which is used to determine the driver's line of sight direction based on the behavior information based on a posture tracking algorithm, and determine the driver's intention to change lanes based on the line of sight direction; a steering wheel state recognition module, which is used to determine the steering wheel holding state based on the steering wheel contact status information; a driving direction recognition module, which is used to determine the vehicle's driving direction based on the driving information; and a correction judgment module, which is used to determine the status of the lane keeping system based on the lane changing intention, the vehicle's driving direction and the steering wheel holding state.

[0012] In one embodiment of the present invention, an electronic device is also provided, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the electronic device implements any of the lane keeping correction methods based on intention recognition described above.

[0013] In one embodiment of the present invention, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes any of the lane keeping correction methods based on intention recognition described above.

[0014] As described above, the lane keeping and deviation correction method, system, device and medium based on intention recognition of the present invention have the following beneficial effects: within the preset sampling time, the driver's behavior information, steering wheel contact state information and driving information are obtained, and the line of sight direction is determined according to the behavior information through the posture tracking algorithm, thereby determining the driver's intention to change lanes, so as to obtain whether the driver changes lanes autonomously. In addition, the steering wheel contact state information and the driving information are used to determine the steering wheel contact state and the driving direction of the vehicle, so as to further confirm the grip state of the steering wheel and the actual driving direction of the vehicle. Combining the above three different dimensions of information, it is possible to accurately determine whether the driver currently has the intention to actively change lanes, thereby determining whether the current lane keeping system status needs to be updated, so as to avoid the situation where the lane keeping system is automatically activated and unnecessary intervention when the driver changes lanes autonomously, which greatly improves the user's driving experience and driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic flow chart of a lane keeping and deviation correction method based on intention recognition provided by an embodiment of the present invention;

[0016] Figure 2 Shown is a structural block diagram of a lane keeping and deviation correction system based on intention recognition provided by an embodiment of the present invention;

[0017] Figure 3 Shown is a structural schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0019] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0020] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0021] The present invention provides a lane keeping and deviation correction method based on intention recognition. Within a preset sampling time, the driver's behavior information, steering wheel contact state information and driving information are obtained, and the line of sight direction is determined according to the behavior information through a posture tracking algorithm, thereby determining the driver's intention to change lanes, and thus whether the driver is changing lanes autonomously can be obtained. In addition, the steering wheel contact state information and the driving information are used to determine the steering wheel contact state and the vehicle's driving direction, thereby further confirming the steering wheel holding state and the vehicle's actual driving direction. Combining the above three different dimensions of information, it is possible to accurately determine whether the driver currently has the intention to actively change lanes, thereby determining whether the current lane keeping system status needs to be updated, so as to avoid the lane keeping system automatically activating and performing unnecessary intervention when the driver changes lanes autonomously, greatly improving the user's driving experience and driving safety.

[0022] See also Figure 1 ,The lane keeping correction method based on intention recognition includes the following steps:

[0023] S1. Within a preset sampling time, obtain the state of the lane keeping system, the driver's behavior information, the steering wheel contact state information and the vehicle's driving information.

[0024] During the preset sampling time, the state of the lane keeping system of the vehicle during the sampling time is detected to confirm whether it is in an activated state. The driver's behavior information during the sampling time is obtained through the driver monitoring system (DMS). The behavior information includes but is not limited to head posture, eye movement information, eye opening and closing status, etc. The steering wheel contact state information is obtained through sensors installed on the steering wheel (such as capacitive sensors or pressure sensors, etc.), wherein the steering wheel contact state information includes but is not limited to the torque applied to the steering wheel by the driver, the grip force, and whether the steering wheel is held, etc. In addition, various dynamic driving information of the vehicle is also obtained, wherein the driving information includes but is not limited to the actual angular velocity and vehicle speed of the vehicle.

[0025] S2. Based on a posture tracking algorithm, determine the driver's line of sight direction according to the behavior information, and determine the driver's lane change intention based on the line of sight direction.

[0026] Based on the posture tracking algorithm and the driver's behavior information, it is judged whether the driver frequently observes the rearview mirror or the side area within the sampling time to determine the driver's line of sight direction and thus determine the driver's intention to change lanes.

[0027] In one embodiment of the present invention, the step of determining the driver's line of sight direction based on the behavior information based on the posture tracking algorithm, and determining the driver's lane change intention based on the line of sight direction includes:

[0028] Based on the identifier of the behavior information, determine the category of the behavior information:

[0029] If the behavior information is eye movement information, then based on the eye gesture tracking method, the driver's sight direction is determined according to the behavior information; wherein the sight direction includes a first perspective, a second perspective, and a third perspective with increasing angles;

[0030] If the behavior information sequence is head information, then based on the head posture tracking method, the driver's line of sight direction is determined according to the behavior information;

[0031] The lane change intention is determined based on the line of sight direction.

[0032] The driver monitoring system will detect the driver's eye state and line of sight or head direction area in real time, and obtain several behavioral information with identification within the preset sampling time. According to the identification of the behavioral information, determine whether the category of the behavioral information is eye movement information or head information. Among them, eye movement information is used to reflect the driver's eye movement and line of sight direction, and head information is used to reflect the driver's head rotation and posture information. It should be noted that, considering that eye movement information can more accurately reflect the driver's line of sight direction, the eye movement information is detected first, and when the eye movement information cannot be detected, the head information is detected. When the behavioral information is eye movement information, the following processing is performed for each behavioral information within the sampling time: Based on the eye posture tracking method, the driver's specific line of sight direction is determined by detecting the driver's iris position, pupil center or eye movement trajectory, wherein the line of sight direction indicates the direction in which the driver's eyes are currently looking. When dividing the line of sight direction, if from the driver's perspective, the line of sight direction is divided into the first perspective, the second perspective and the third perspective in the clockwise direction according to the increasing angle. Exemplarily, the first perspective is the left line of sight, indicating that the driver's line of sight is toward the left side of the vehicle, the second perspective is the central line of sight, indicating that the driver's line of sight is facing forward, and the third perspective is the right line of sight, indicating that the driver's line of sight is toward the right side of the vehicle. When the behavior information is head information, based on the head posture tracking method, the driver's line of sight direction is determined by monitoring the deflection angle and position change of the driver's head. Among them, the head information includes the head rotation angle and the head position change. Exemplarily, when the driver's head deflects to the left or right, it can be determined whether the driver is observing the left or right rearview mirror based on the deflection angle and the current position of the head. After each behavior information within the sampling time is analyzed, the line of sight direction corresponding to each behavior information is summarized, and the adjacent identical line of sight directions are merged into one line of sight direction. After all line of sight directions are processed, the driver's line of sight changes within the sampling time can be obtained, thereby determining the intention to change lanes.

[0033] Furthermore, the posture tracking algorithm is based on the behavior information to determine the driver's line of sight direction, and based on the line of sight direction to determine the driver's intention to change lanes, and further includes: detecting the open or closed state of the eyes, thereby determining whether the driver keeps his eyes open, and switching the line of sight between different driving areas to determine the driver's intention to change lanes. Among them, the driving task area includes but is not limited to the left and right rearview mirrors, the interior rearview mirror, and the windshield division area.

[0034] In one embodiment of the present invention, determining the lane change intention based on the line of sight direction includes:

[0035] Counting the number of times the sight line direction switches from the second viewing angle to the first viewing angle, and the number of times the sight line direction switches from the second viewing angle to the third viewing angle within the sampling time;

[0036] Determine whether the number of times the sight line direction is switched from the second viewing angle to the first viewing angle / from the second viewing angle to the third viewing angle within the sampling time is greater than a preset number threshold:

[0037] If so, the corresponding first-perspective / third-perspective is regarded as the lane-changing intention;

[0038] Otherwise, continue to determine the driver's sight direction according to the behavior information within the next sampling time.

[0039] Count the changes in the sight direction within the current sampling time (such as 20 seconds), record the number of times the sight switches from the second perspective (such as the central sight) to the first perspective (such as the left side sight), and the number of times the sight switches from the second perspective to the third perspective (such as the right side sight). Determine whether the number of times the driver's sight switches from the second perspective to the first perspective or from the first perspective to the third perspective within the sampling time is greater than the number threshold (such as 2 times): if the number of switches is greater than the number threshold, it means that the driver has the intention to change lanes to the left or right; otherwise, it means that the driver does not have the intention to change lanes, and the behavior information within the next sampling time can be monitored for judgment. Further, the driver's intention to change lanes can also be determined based on the number of times the second perspective is switched to the first perspective (or the third perspective) and the number of times the first perspective (or the third perspective) is switched to the second perspective. Exemplarily, within the current sampling time of 20 seconds, if it is determined that the driver's sight switches back and forth between the front windshield area and the right rearview mirror area more than 2 times, it is considered that the driver has the intention to change lanes to the right.

[0040] S3. Determine a steering wheel contact state based on the steering wheel contact state information.

[0041] Specifically, in an embodiment of the present invention, determining the steering wheel holding state based on the steering wheel contact state information includes:

[0042] Determine whether the steering wheel contact state information is greater than or equal to a preset contact state threshold:

[0043] If yes, the steering wheel is in a gripping state;

[0044] Otherwise, the steering wheel is in a non-holding state.

[0045] The hand torque applied by the driver on the steering wheel is detected by PSCM (Power Steering Control Module) or HOD (Handsoff detection). Exemplarily, a sensor (such as a pressure sensor) installed on the steering wheel or a capacitive sensor on a capacitive steering wheel monitors the contact between the driver's hand and the steering wheel in real time. If the contact state information is greater than or equal to the preset contact state threshold, it means that the contact area or pressure between the driver's hand and the steering wheel has reached the preset holding standard, indicating that the driver is holding the steering wheel and has autonomous driving awareness. On the contrary, if the contact state information is less than the contact state threshold, it means that the contact area or pressure between the driver's hand and the steering wheel is insufficient, indicating that the driver may not be holding the steering wheel at this moment or is in a state of lightly touching the steering wheel, and the autonomous driving awareness is insufficient. LKA can be used to correct the current vehicle driving state later. It can be understood that the specific value of the contact state threshold is not limited, and those skilled in the art can choose based on the experimental data or the adaptability of the driving scene, which is not limited here.

[0046] S4. Determine the driving direction of the vehicle based on the driving information.

[0047] Specifically, in an embodiment of the present invention, determining the driving direction of the vehicle based on the driving information includes:

[0048] Regarding the steering wheel hand torque in the driving information:

[0049] Determine whether the steering wheel hand torque is greater than or equal to a preset first threshold:

[0050] If yes, marking the steering wheel hand torque as the first steering wheel hand torque;

[0051] Otherwise, determine whether the steering wheel hand torque is less than or equal to a preset second threshold:

[0052] If yes, marking the steering wheel hand torque as a second steering wheel hand torque;

[0053] Otherwise, continue to judge the next steering wheel hand torque;

[0054] Counting the total amount of the first steering wheel hand torque and the total amount of the second steering wheel hand torque;

[0055] The driving direction of the vehicle is determined based on the total amount of the first steering wheel hand torque and the total amount of the second steering wheel hand torque.

[0056] When the driving information is the steering wheel hand torque, for each steering wheel hand torque within the sampling time: determine whether the steering wheel hand torque is greater than or equal to the first threshold value. If so, it means that the driver is steering in the first direction (left or right), and it can be marked as the first steering wheel hand torque. On the contrary, if the steering wheel hand torque is less than the first threshold value, further analysis and judgment are required to determine whether the steering wheel hand torque is less than or equal to the second threshold value: if so, it means that the driver is steering in the second direction, and it can be marked as the second steering wheel hand torque; on the contrary, if the steering wheel hand torque is greater than the second threshold value, continue to select the next steering wheel hand torque for analysis. Among them, the first direction is opposite to the second direction (such as the first direction is the left side and the second direction is the right side). After all steering wheel hand torques within the sampling time are analyzed, the total amount of the first steering wheel hand torque and the total amount of the second steering wheel hand torque are counted to determine the driving direction of the vehicle. Among them, the total amount of the first steering wheel hand torque represents the total torque applied by the driver in the first direction within the sampling period, and the total amount of the second steering wheel hand torque represents the total torque applied by the driver in the second direction within the sampling period.

[0057] In one embodiment of the present invention, determining the driving direction of the vehicle based on the total amount of the first steering wheel hand torque and the total amount of the second steering wheel hand torque includes:

[0058] Determine whether the total amount of the first steering wheel hand torque is greater than or equal to a preset first total amount threshold:

[0059] If yes, the driving direction is determined as changing lanes in the first direction;

[0060] Otherwise, it is determined whether the total amount of the second steering wheel hand torque is greater than or equal to a preset second total amount threshold:

[0061] If yes, the driving direction is determined as changing lanes to a second direction; wherein the first direction is opposite to the second direction;

[0062] Otherwise, the driving direction is determined to be straight ahead.

[0063] If the total amount of the first steering wheel hand torque is greater than the first total amount threshold, it means that the driver has the intention to change lanes in the first direction (such as left) during the current sampling time, so the vehicle's driving direction is determined to be changing lanes in the first direction. On the contrary, when the total amount of the first steering wheel hand torque is less than the first total amount threshold, it is necessary to continue to determine whether the total amount of the second steering wheel hand torque is greater than or equal to the second total amount threshold: if so, it means that the driver has the intention to change lanes in the second direction (such as right) during the current sampling time, so the vehicle's driving direction is determined to be changing lanes in the second direction. On the contrary, if the total amount of the second steering wheel hand torque is less than the second total amount threshold, it means that the driver has no obvious steering operation during the current sampling time, so the driving direction can be determined as straight.

[0064] S5. Update the state of the lane keeping system based on the lane change intention, the driving direction of the vehicle and the steering wheel contact state.

[0065] The lane change intention can be used to determine whether the driver intends to change lanes autonomously. The vehicle's driving direction can be used to further determine the vehicle's lane change situation. The steering wheel contact state can be used to further determine whether the driver is holding the steering wheel, thereby inferring whether the driver intends to change lanes autonomously. Combining the above three pieces of information, it can be determined whether the current lane change behavior is an autonomous lane change or an involuntary lane change, thereby updating the state of the lane keeping system.

[0066] In one embodiment of the present invention, updating the state of the lane keeping system based on the lane change intention, the driving direction of the vehicle and the steering wheel contact state includes:

[0067] If the lane change intention is the same as the driving direction and the steering wheel is in a held state, keeping the lane keeping system in a disabled state;

[0068] If the lane change intention is different from the driving direction and / or the steering wheel is in a non-held state, the lane keeping system is activated.

[0069] If the lane change intention is the same as the vehicle's driving direction, and the steering wheel is in a held state, it means that the driver is currently holding the steering wheel to participate in vehicle control, which means that the driver is autonomously controlling the vehicle, so there is no need for the lane keeping system to intervene and it can be kept in a disabled state. On the contrary, if the lane change intention (such as changing lanes to the left) and the driving direction (such as driving to the right) are opposite, or the direction is not held, or both, it means that the driver is not currently holding the steering wheel, the vehicle is in an unmanned control stage, or there is a deviation between the driver's intention and the actual driving direction of the vehicle. At this time, in order to ensure driving safety, the lane keeping system needs to be activated so that the vehicle automatically performs lane keeping or deviation correction operations to ensure that the vehicle is driving in the lane and avoid deviation or accidents.

[0070] It should be noted that in the present invention, the input value and direction of the driver's steering wheel angle and hand torque can also be judged based on other vehicle parameters, and compared with the actual motion trajectory direction of the real vehicle, so as to judge whether the output is a lane deviation actively input by the driver. Among them, other vehicle parameters include but are not limited to the lateral acceleration of the vehicle, other target attribute parameters around the vehicle (position, direction, speed, acceleration, etc.), surrounding environment space detection, etc.

[0071] As a specific example of this solution, when the driver's eyes are open and the monitoring eye sight is in the front windshield or rearview mirror and the preset driving task area, the probability distribution is biased towards the subsequent steering input direction.dmm = 20s, the number of times the line of sight switches back and forth between the front windshield area and the left rearview mirror area n ≥ 2 times, then the output signal of the DMS prediction that the driver has the intention to actively turn left / change lanes is to change lanes left, until the driver's line of sight returns to the front windshield area T ≥ 25s, then it is considered that normal driving is at this time, and the output signal a = default. dmm = 20s, the sight switches back and forth between the front windshield area and the right rearview mirror area n≥2 times, then the output signal a=right is output by DMS to predict that the driver has the intention to actively turn left / change lanes, until the driver's sight returns to the front windshield area T≥25s, and the output signal a=default. The PSCM or HOD module detects the absolute value of the hand torque Tdriver applied by the driver on the steering wheel |T driver |≥0.3Nm and lasts for 100ms or detects in real time whether the driver is holding the steering wheel through a capacitive steering wheel or other systems, as the basic input for whether the driver actively deviates from the lane; outputs the detection result signal b=handson, indicating that the driver is holding the steering wheel; or b=handsoff, indicating that the driver is not holding the steering wheel. The PSCM module monitors the driver's active hand torque input, actual angular velocity input, etc. in real time, T driver ≥1.2Nm and lasts for 200ms, indicating that the driver actively pulls the steering wheel to the left; T driver ≤-1.2Nm and lasts for 200ms, indicating that the driver actively pulls the steering wheel to the right. Agspd>0 indicates that the instantaneous actual vehicle turning angle input is to the left; Agspd<0 indicates that the instantaneous actual vehicle turning angle input is to the right. The LKA triggering suppression conditions for the left lane of the vehicle must simultaneously meet the following: a=left, b=handson, T driver ≥1.2Nm and last for 200ms, Agspd>0. The LKA triggering and suppression conditions for the right lane of the vehicle must meet the following conditions at the same time: a=right, b=handson, T driver ≤-1.2Nm and last for 200ms, Agspd<0. When the LKA trigger inhibition condition of the left lane of the vehicle or the LKA trigger inhibition condition of the right lane of the vehicle is detected, the LKA trigger will be suppressed and the driver will drive autonomously.

[0072] See also Figure 2The lane keeping and deviation correction system 100 based on intention recognition includes: a data acquisition module 110, a driver behavior recognition module 120, a steering wheel state recognition module 130, a driving direction recognition module 140, and a deviation correction judgment module 150. The above-mentioned data acquisition module 110 is used to obtain the state of the lane keeping system, the driver's behavior information, the steering wheel contact state information and the driving information of the vehicle within a preset sampling time. The driver behavior recognition module 120 is used to determine the driver's line of sight direction according to the behavior information based on the posture tracking algorithm, and determine the driver's intention to change lanes based on the line of sight direction. The steering wheel state recognition module 130 is used to determine the steering wheel holding state based on the steering wheel contact state information. The driving direction recognition module 140 is used to determine the driving direction of the vehicle based on the driving information. The deviation correction judgment module 150 is used to determine the state of the lane keeping system based on the lane change intention, the driving direction of the vehicle and the steering wheel holding state.

[0073] For the specific limitations of the lane keeping and correction system based on intention recognition, please refer to the limitations of the lane keeping and correction method based on intention recognition above, which will not be repeated here. The various modules in the above-mentioned lane keeping and correction system based on intention recognition can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware format, or can be stored in the memory of the computer device in software format, so that the processor can call the operations corresponding to the above modules.

[0074] It should be noted that, in order to highlight the innovative part of the present invention, the present embodiment does not introduce modules that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other modules in the present embodiment.

[0075] See also Figure 3 The electronic device 1 may include a memory 12, a processor 13 and a bus, and may also include a computer program stored in the memory 12 and executable on the processor 13, such as a lane keeping correction program based on intention recognition.

[0076] Among them, the memory 12 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 12 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 12 can also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 12 can not only be used to store application software and various types of data installed in the electronic device 1, such as lane keeping correction codes based on intention recognition, etc., but can also be used to temporarily store data that has been output or is to be output.

[0077] In some embodiments, the processor 13 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 13 is the control core (Control Unit) of the electronic device 1, and uses various interfaces and lines to connect the various components of the entire electronic device 1, and executes or executes programs or modules stored in the memory 12 (such as lane keeping correction programs based on intention recognition, etc.), and calls data stored in the memory 12 to execute various functions of the electronic device 1 and process data.

[0078] The processor 13 executes the operating system and various installed applications of the electronic device 1. The processor 13 executes the applications to implement the steps in the lane keeping and deviation correction method based on intention recognition.

[0079] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory 12 and executed by the processor 13 to complete the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the electronic device 1. For example, the computer program may be divided into a data acquisition module 110, a driver behavior recognition module 120, a steering wheel state recognition module 130, a driving direction recognition module 140, and a deviation correction judgment module 150.

[0080] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium, and the computer-readable storage medium can be non-volatile or volatile. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to perform part of the functions of the lane keeping correction method based on intention recognition described in various embodiments of the present application.

[0081] In summary, the lane keeping correction method, system, device and medium based on intention recognition disclosed in the present invention monitors the driver's eye state, gaze area, contact between the hand and the steering wheel, input direction and size of the steering wheel hand torque and other information in real time through a variety of sensors installed on the whole vehicle, and compares the monitored information with the actual motion trajectory trend of the vehicle to determine whether the driver actively deviates from the lane. And based on the judgment result, it is determined whether to suppress the state machine of the lane keeping system to avoid excessive intervention. The present invention improves the situation that when the driver deviates from the lane voluntarily, the lane keeping assist system will actively activate and intervene, resulting in a situation where the driver competes with the driver for the steering wheel. The driving experience is greatly improved, the functional applicability and user experience of the lane keeping system are improved, and the problem of the driver's unwillingness to use the lane keeping system due to excessive unnecessary intervention is avoided. Therefore, the present invention effectively overcomes the various shortcomings in the prior art and has a high industrial utilization value.

[0082] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A lane keeping correction method based on intention recognition, characterized in that: The method comprises: Within a preset sampling time, the lane keeping system status, driver behavior information, steering wheel contact status information, and vehicle driving information are obtained; Based on a posture tracking algorithm, determining the driver's line of sight direction according to the behavior information, and determining the driver's lane change intention based on the line of sight direction; determining a steering wheel contact state based on the steering wheel contact state information; Determining a driving direction of the vehicle based on the driving information; Based on the lane change intention, the driving direction of the vehicle and the steering wheel contact state, a state of a lane keeping system is updated.

2. The lane keeping correction method based on intention recognition according to claim 1, characterized in that: The method of determining the driver's sight direction based on the behavior information based on the posture tracking algorithm, and determining the driver's lane change intention based on the sight direction, includes: Based on the identifier of the behavior information, determine the category of the behavior information: If the behavior information is eye movement information, then based on the eye gesture tracking method, the driver's sight direction is determined according to the behavior information; wherein the sight direction includes a first perspective, a second perspective, and a third perspective with increasing angles; If the behavior information sequence is head information, then based on the head posture tracking method, the driver's line of sight direction is determined according to the behavior information; The lane change intention is determined based on the line of sight direction.

3. The lane keeping correction method based on intention recognition according to claim 2 is characterized in that: The determining the lane change intention based on the line of sight direction includes: Counting the number of times the sight line direction switches from the second viewing angle to the first viewing angle, and the number of times the sight line direction switches from the second viewing angle to the third viewing angle within the sampling time; Determine whether the number of times the sight line direction is switched from the second viewing angle to the first viewing angle / from the second viewing angle to the third viewing angle within the sampling time is greater than a preset number threshold: If so, the corresponding first-perspective / third-perspective is regarded as the lane-changing intention; Otherwise, continue to determine the driver's sight direction according to the behavior information within the next sampling time.

4. The lane keeping and deviation correction method based on intention recognition according to claim 1, characterized in that: The determining the steering wheel holding state based on the steering wheel contact state information includes: Determine whether the steering wheel contact state information is greater than or equal to a preset contact state threshold: If yes, the steering wheel is in a gripping state; Otherwise, the steering wheel is in a non-holding state.

5. The lane keeping and deviation correction method based on intention recognition according to claim 1, characterized in that: The determining the driving direction of the vehicle based on the driving information includes: Regarding the steering wheel hand torque in the driving information: Determine whether the steering wheel hand torque is greater than or equal to a preset first threshold: If yes, marking the steering wheel hand torque as the first steering wheel hand torque; Otherwise, determine whether the steering wheel hand torque is less than or equal to a preset second threshold: If yes, marking the steering wheel hand torque as a second steering wheel hand torque; Otherwise, continue to judge the next steering wheel hand torque; Counting the total amount of the first steering wheel hand torque and the total amount of the second steering wheel hand torque; The driving direction of the vehicle is determined based on the total amount of the first steering wheel hand torque and the total amount of the second steering wheel hand torque.

6. The lane keeping and deviation correction method based on intention recognition according to claim 5 is characterized in that: The determining the driving direction of the vehicle based on the total amount of the first steering wheel hand torque and the total amount of the second steering wheel hand torque includes: Determine whether the total amount of the first steering wheel hand torque is greater than or equal to a preset first total amount threshold: If yes, the driving direction is determined as changing lanes in the first direction; Otherwise, it is determined whether the total amount of the second steering wheel hand torque is greater than or equal to a preset second total amount threshold: If yes, the driving direction is determined as changing lanes to a second direction; wherein the first direction is opposite to the second direction; Otherwise, the driving direction is determined to be straight ahead.

7. The lane keeping and deviation correction method based on intention recognition according to claim 1, characterized in that: The updating of the state of the lane keeping system based on the lane change intention, the driving direction of the vehicle and the steering wheel contact state includes: If the lane change intention is the same as the driving direction and the steering wheel is in a held state, keeping the lane keeping system in a disabled state; If the lane change intention is different from the driving direction and / or the steering wheel is in a non-held state, the lane keeping system is activated.

8. A lane keeping and deviation correction system based on intention recognition, characterized in that: The system comprises: A data acquisition module, used to acquire the state of the lane keeping system, the driver's behavior information, the steering wheel contact state information and the vehicle's driving information within a preset sampling time; A driver behavior recognition module, configured to determine the driver's line of sight direction according to the behavior information based on a posture tracking algorithm, and determine the driver's lane change intention based on the line of sight direction; A steering wheel state recognition module, used to determine a steering wheel holding state based on the steering wheel contact state information; A driving direction identification module, used to determine the driving direction of the vehicle based on the driving information; The deviation correction judgment module is used to determine the state of the lane keeping system based on the lane change intention, the vehicle's driving direction and the steering wheel holding state.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the lane keeping correction method based on intention recognition as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the lane keeping correction method based on intention recognition as described in any one of claims 1 to 7.