Driver hands-off detection method and device, lane keeping method and system

Abstract

A driver's hands-off detection method, a driver's hands-off detection device, a lane keeping method and a lane keeping system. The driver's hands-off detection method comprises: obtaining wheel speed information and driver's hand torque information; determining whether the driver has taken his hands off the steering wheel according to the wheel speed information and the hand torque information. This solution can infer the current road surface flatness condition according to the wheel speed information, and then reasonably determine the hands-off judgment threshold according to different road surface conditions, thereby improving the accuracy of the hands-off judgment and improving the safety and user experience of the LKS function.

Description

Technical Field

[0001] The present invention relates to but is not limited to intelligent driving technology, and in particular to a driver's hands-off detection method, a driver's hands-off detection device, a lane keeping method and a lane keeping system. Background Art

[0002] At present, the system usually determines whether the driver has taken his hands off the steering wheel based on the detection results of the hand torque sensor. However, the hand torque sensor is a torque sensor and is easily affected by the road surface. When the road surface is uneven, the torque sensor value will change significantly, which will mislead the system to determine whether the driver has taken his hands off the steering wheel, resulting in misjudgment, affecting user safety and reducing the user experience. Summary of the invention

[0003] The embodiments of the present application provide a driver hands-off detection method, a driver hands-off detection device, a lane keeping method and a lane keeping system, which can improve the accuracy of driver hands-off judgment, thereby improving user safety and user experience.

[0004] An embodiment of the present application provides a method for detecting a driver's hands-off steering wheel, comprising: obtaining wheel speed information and driver's hand torque information; and determining whether the driver has taken his hands off the steering wheel based on the wheel speed information and the hand torque information.

[0005] The driver's hands-off detection method provided in the embodiment of the present application can comprehensively combine the wheel speed information and the driver's hand torque information to determine whether the driver has taken his hands off the steering wheel. Therefore, the wheel speed information and the hand torque information can be used together as a basis for determining whether the driver has taken his hands off the steering wheel. Since the wheel speed information can reflect the vibration of the wheel, and thus indirectly reflect the flatness of the current road surface, in the process of determining whether the driver has taken his hands off the steering wheel, the flatness of the current road surface can be inferred based on the wheel speed information, and then the driver's hands can be comprehensively determined based on the flatness of the current road surface and the driver's hand torque. In this way, whether the driver has taken his hands off takes into account the driver's hand torque and the flatness of the current road surface, which is conducive to reducing the adverse effect of road surface flatness on determining whether the driver has taken his hands off the steering wheel, improving the accuracy of hands-off judgment, and thus improving user safety and user experience.

[0006] Moreover, compared with using an acceleration sensor to estimate the smoothness of the road surface, the embodiment of the present application estimates the smoothness of the current road surface through wheel speed information, that is, estimates the smoothness of the road surface through the signal of the wheel speed sensor. Since the acceleration sensor is mounted on the vehicle body and is relatively far from the ground, it will detect vehicle body vibrations other than steering wheel vibrations and is subject to more interference. As the sensor closest to the ground, the wheel speed sensor has a greater advantage than other sensors when used to monitor the road surface status and is less affected by other factors. Therefore, it is more accurate in estimating the road surface smoothness.

[0007] In addition, compared to inferring the road surface state through changes in the LKS steering control torque, this solution uses the signal of the wheel speed sensor to infer the road surface state. When the lane line recognition result is unstable or the road slope changes suddenly, the LKS steering control torque will change significantly. Therefore, it is impossible to accurately infer the road surface state through changes in the LKS steering control torque, and the possibility of misjudgment of hands-off is high. This solution uses the signal of the wheel speed sensor to infer the road surface state, which can eliminate the influence other than road surface excitation, thereby accurately inferring the road surface state and improving the accuracy of hands-off judgment.

[0008] In an exemplary embodiment, determining whether the driver has taken their hands off the steering wheel based on the wheel speed information and the hand torque information includes: determining a hands-off determination threshold based on the wheel speed information; and determining whether the driver has taken their hands off the steering wheel based on the hands-off determination threshold and the hand torque information.

[0009] In an exemplary embodiment, determining the hands-off determination threshold value based on the wheel speed information includes: determining the vibration degree of the wheel based on the wheel speed information; determining a hands-off determination threshold reference value based on the vibration degree of the wheel; and determining the hands-off determination threshold based on the hands-off determination threshold reference value.

[0010] In an exemplary embodiment, determining the hands-off determination threshold based on the hands-off determination threshold reference value includes: judging whether the hands-off determination threshold reference value has been maintained for a set time period; determining the hands-off determination threshold reference value as a new hands-off determination threshold based on that the hands-off determination threshold reference value has been maintained for a set time period; and continuing to use the hands-off determination threshold determined last time based on that the hands-off determination threshold reference value has not been maintained for a set time period.

[0011] In an exemplary embodiment, determining a hands-off determination threshold reference value based on the vibration degree of the wheel includes: determining hands-off determination threshold adjustment information based on the vibration degree of the wheel; and determining the hands-off determination threshold reference value based on the hands-off determination threshold adjustment information.

[0012] In an exemplary embodiment, the hands-off determination threshold adjustment information is: an updated value of the hands-off determination threshold reference value; determining the hands-off determination threshold reference value based on the hands-off determination threshold adjustment information includes: determining the updated value of the hands-off determination threshold reference value as the hands-off determination threshold reference value; or, the hands-off determination threshold adjustment information is: a hands-off determination threshold reference value coefficient; determining the hands-off determination threshold reference value based on the hands-off determination threshold adjustment information includes: determining the product of a hands-off determination threshold base value and the hands-off determination threshold reference value coefficient as the hands-off determination threshold reference value.

[0013] In an exemplary embodiment, determining the hands-off determination threshold adjustment information according to the vibration degree of the wheel includes: determining the hands-off determination threshold adjustment information corresponding to the vibration degree of the wheel according to a mapping relationship between the vibration degree of the wheel and the hands-off determination threshold adjustment information.

[0014] In an exemplary embodiment, the mapping relationship between the wheel vibration degree and the hands-off determination threshold adjustment information is based on the wheel vibration degree and the road surface.

[0015] The correspondence between the flatness level and the hands-off determination threshold adjustment information is obtained; wherein, the road surface flatness level is negatively correlated with the road surface flatness, the vibration degree of the wheel is negatively correlated with the road surface flatness, the hands-off determination threshold reference value is positively correlated with the road surface flatness level, and the hands-off determination threshold adjustment information is positively correlated with the hands-off determination threshold reference value.

[0016] In an exemplary embodiment, the road surface flatness levels include: level one, level two and level three, the road surface flatness of level one is better than that of level two, and the road surface flatness of level two is better than that of level three; the hands-off determination threshold adjustment information includes: first adjustment information, second adjustment information and third adjustment information, the first adjustment information < the second adjustment information < the third adjustment information; in the mapping relationship between the vibration degree of the wheel and the hands-off determination threshold adjustment information: when the vibration degree of the wheel is less than the first vibration degree, the hands-off determination threshold adjustment information is equal to the first adjustment information; when the vibration degree of the wheel is greater than the first vibration degree and less than the second vibration degree, the hands-off determination threshold adjustment information is equal to the second adjustment information, and the second vibration degree is stronger than the first vibration degree; when the vibration degree of the wheel is greater than the second vibration degree, the hands-off determination threshold adjustment information is equal to the third adjustment information.

[0017] In an exemplary embodiment, determining whether the driver takes their hands off the steering wheel based on the hands-off determination threshold and the hand torque information includes: comparing the hand torque information with the hands-off determination threshold; and determining whether the driver takes their hands off the steering wheel based on the comparison result.

[0018] In an exemplary embodiment, determining the vibration degree of the wheel according to the wheel speed information includes: filtering the wheel speed information; and determining the vibration degree of the wheel according to a result of the filtering process.

[0019] In an exemplary embodiment, the wheel speed information is an average value of wheel speed information of a plurality of wheels of the vehicle.

[0020] An embodiment of the present application also provides a lane keeping method, comprising: determining whether the driver has taken his hands off the steering wheel according to the driver hands-off detection method described in any one of the above embodiments; and exiting the lane keeping function based on the driver taking his hands off the steering wheel.

[0021] An embodiment of the present application also provides a lane keeping system, including: a hand torque detection device, configured to detect the hand torque of the driver; a wheel speed detection device, configured to detect the wheel speed; and a lane keeping control device, configured to: obtain wheel speed information and the driver's hand torque information according to the detection results of the wheel speed detection device and the hand torque detection device, and determine whether the driver takes his hands off the steering wheel according to the wheel speed information and the hand torque information, and control whether the lane keeping function is exited according to the detection results of the driver's hands-off detection module.

[0022] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by implementing the present application. Other advantages of the present application can be realized and obtained by the schemes described in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide an understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0024] Figure 1 A schematic diagram of a process flow of a driver's hands-off detection method provided in one embodiment of the present application;

[0025] Figure 2 It is a schematic diagram of the driver's hand torque signal when driving on a good road;

[0026] Figure 3 It is a schematic diagram of the driver's hand torque signal when driving on a bad road;

[0027] Figure 4 A schematic diagram of the relationship between the vibration degree of the wheel and the reference value of the hands-off determination threshold;

[0028] Figure 5 A schematic diagram of the structure of a driver's hands-off detection device provided in one embodiment of the present application;

[0029] Figure 6 A schematic diagram of a vehicle provided for one embodiment of the present application;

[0030] Figure 7 A schematic diagram of a vehicle provided for one embodiment of the present application;

[0031] Figure 8 A schematic diagram of the principles of a lane keeping system provided for one embodiment of the present application.

[0032] 101 turn signal switch, 102 accelerator pedal sensor, 103 brake pedal sensor, 104 steering angle sensor, 105 hand torque sensor, 106 vehicle speed sensor, 107 radar sensor, 108 camera sensor, 109 yaw rate sensor, 110 longitudinal acceleration sensor, 111 lateral acceleration sensor, 112 right front wheel speed sensor, 113 left front wheel speed sensor, 114 right rear wheel speed sensor, 115 left rear wheel speed sensor;

[0033] 1071 a first radar sensor, 1072 a second radar sensor, 1073 a third radar sensor, 1074 a fourth radar sensor, 1075 a fifth radar sensor, 1076 a sixth radar sensor, 1081 a first camera sensor, 1082 a second camera sensor, 1083 a third camera sensor;

[0034] 200 driving assistance control device, 201 lane keeping control device, 2011 lane keeping control module, 2021 low-pass filter processing module, 2022 high-pass filter processing module, 2023 calculation module, 2024 hands-off judgment threshold determination module, 205 processor, 206 memory;

[0035] 301 engine ECU, 311 engine, 302 brake ECU, 312 brake system, 303 steering ECU, 313 steering system, 304 information display ECU, 314 information display device;

[0036] 400 driving environment condition detection device, 410 hand torque detection device. DETAILED DESCRIPTION

[0037] The present application describes multiple embodiments, but the description is exemplary rather than restrictive, and it is obvious to those skilled in the art that there may be more embodiments and implementations within the scope of the embodiments described in the present application. Although many possible feature combinations are shown in the drawings and discussed in the specific embodiments, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with any other feature or element in any other embodiment, or may replace any other feature or element in any other embodiment.

[0038] The present application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The embodiments, features and elements disclosed in the present application may also be combined with any conventional features or elements to form a unique invention scheme defined by the claims. Any features or elements of any embodiment may also be combined with features or elements from other invention schemes to form another unique invention scheme defined by the claims. Therefore, it should be understood that any feature shown and / or discussed in the present application may be implemented individually or in any appropriate combination. Therefore, except for the limitations made according to the attached claims and their equivalents, the embodiments are not subject to other restrictions. In addition, various modifications and changes may be made within the scope of protection of the attached claims.

[0039] In addition, when describing representative embodiments, the specification may have presented the method and / or process as a specific sequence of steps. However, to the extent that the method or process does not rely on the specific order of the steps described herein, the method or process should not be limited to the steps of the specific order described. As will be understood by those of ordinary skill in the art, other sequences of steps are also possible. Therefore, the specific sequence of the steps set forth in the specification should not be interpreted as a limitation to the claims. In addition, the claims for the method and / or process should not be limited to the steps of performing them in the order written, and those skilled in the art can easily understand that these sequences can be changed and still remain within the spirit and scope of the embodiments of the present application.

[0040] The functions of the driving assistance (ADAS, Advanced Driving Assistance System) include the LKS (Lane Keeping System) function, which assists steering control to keep the vehicle in the center of the lane. The execution of this function requires the system to provide lane centering assistance under the premise that the driver is in control of the steering wheel. This function identifies the lane line ahead through driving environment condition detection devices such as cameras, and uses EPS (Electric Power Steering, electric power steering system) to control the vehicle to drive in the center of the lane. According to regulatory requirements, the lane centering function needs to be suppressed when it detects that the driver has taken off the hands, that is, the lane keeping function needs to be automatically exited.

[0041] At present, the system usually directly judges whether the driver has taken his hands off the steering wheel based on the detection results of the hand torque sensor. However, the hand torque sensor is a torque sensor and is easily affected by the road surface. When the road surface is uneven, the torque sensor value will change significantly, which will mislead the system to judge whether the driver has taken his hands off the steering wheel and cause misjudgment, affecting user safety and user experience.

[0042] The driver hands-off detection method provided in the embodiment of the present application can solve the above-mentioned problems, improve the accuracy of driver hands-off detection, and reduce missed alarms and false alarms of hands-off detection.

[0043] like Figure 1 As shown, the embodiment of the present application provides a method for detecting a driver's hands-off state, comprising:

[0044] Step S10: obtaining wheel speed information and driver's hand torque information;

[0045] Step S20: Determine whether the driver has taken his hands off the steering wheel based on the wheel speed information and the hand torque information.

[0046] The wheel speed information can be obtained through the signal of the wheel speed sensor, and the driver's hand torque information can be obtained through the hand torque sensor.

[0047] The driver's hands-off detection method provided in the embodiment of the present application can comprehensively combine the wheel speed information and the driver's hand torque information to determine whether the driver has taken his hands off the steering wheel. Therefore, the wheel speed information and the hand torque information can be used together as a basis for determining whether the driver has taken his hands off the steering wheel. Since the wheel speed information can reflect the vibration of the wheel, and thus indirectly reflect the flatness of the current road surface, in the process of determining whether the driver has taken his hands off the steering wheel, the flatness of the current road surface can be inferred based on the wheel speed information, and then the driver's hands can be comprehensively determined based on the flatness of the current road surface and the driver's hand torque. In this way, whether the driver has taken his hands off takes into account the driver's hand torque and the flatness of the current road surface, which is conducive to reducing the adverse effect of road surface flatness on determining whether the driver has taken his hands off the steering wheel, improving the accuracy of hands-off judgment, and thus improving user safety and user experience.

[0048] Moreover, compared with using an acceleration sensor to estimate the smoothness of the road surface, the embodiment of the present application estimates the smoothness of the current road surface through wheel speed information, that is, estimates the smoothness of the road surface through the signal of the wheel speed sensor. Since the acceleration sensor is mounted on the vehicle body and is relatively far from the ground, it will detect vehicle body vibrations other than steering wheel vibrations and is subject to more interference. As the sensor closest to the ground, the wheel speed sensor has a greater advantage than other sensors when used to monitor the road surface status and is less affected by other factors. Therefore, it is more accurate in estimating the road surface smoothness.

[0049] In addition, compared to inferring the road surface state through changes in the LKS steering control torque, this solution uses the signal of the wheel speed sensor to infer the road surface state. When the lane line recognition result is unstable or the road slope changes suddenly, the LKS steering control torque will change significantly. Therefore, it is impossible to accurately infer the road surface state through changes in the LKS steering control torque, and the possibility of misjudgment of hands-off is high. This solution uses the signal of the wheel speed sensor to infer the road surface state, which can eliminate the influence other than road surface excitation, thereby accurately inferring the road surface state and improving the accuracy of hands-off judgment.

[0050] In an exemplary embodiment, determining whether the driver has taken his hands off the steering wheel according to wheel speed information and hand torque information includes:

[0051] Determine a hands-off judgment threshold according to wheel speed information;

[0052] Determine whether the driver has taken their hands off the steering wheel based on the hands-off determination threshold and hand torque information.

[0053] After research, it was found that the driver's hand torque signal is significantly different when driving on roads of different conditions. Figure 2 Schematic diagram of the driver's hand torque signal when driving on a good road. Figure 3 The figure is a schematic diagram of the hand torque signal when the driver takes the hands off the car while driving on a bad road. It can be seen that when driving on a good road, the detection value of the hand torque sensor is small and the fluctuation range is small. When driving on a bad road, the detection value of the hand torque sensor is large and the fluctuation range is large. The hands-off judgment threshold is recorded as Kon. When it exceeds ±Kon, the hand torque value is large and it can be judged that the hands are not taken off; when it is between -Kon and Kon, the hand torque value is small and it can be judged that the hands are taken off.

[0054] Therefore, when driving on a good road, if Kon is set too large, the detection value of the hand torque sensor is difficult to exceed ±Kon, so it is difficult to determine that the hands are not released, and it is easy to determine that the hands are released. Therefore, even if the driver does not release the hands on a good road, it may be misjudged as a hands-off, resulting in the lane keeping function being frequently suppressed and affecting the user experience. To prevent such misjudgments, the hands-off judgment threshold when driving on a good road needs to be set as small as possible.

[0055] When driving on a bad road, if the hands-off judgment threshold for a good road is used, the detection value of the hands-off torque sensor on a bad road is very likely to exceed ±Kon, so it is easy to judge that the hands are not taken off, and it is difficult to judge that the hands are taken off. Therefore, even if the driver takes the hands off on a bad road, it may be misjudged as not taking the hands off, causing the lane keeping function to continue to operate when the driver takes the hands off the steering wheel, affecting user safety. Therefore, it is necessary to increase the hands-off judgment threshold to Kon1, such as Figure 3 shown.

[0056] Therefore, this scheme first determines the hands-off judgment threshold based on the wheel speed information to ensure that the determined hands-off judgment threshold matches the road condition reflected by the wheel speed information, and then determines whether the driver has let go of the steering wheel based on the hands-off judgment threshold and the hand torque information, thereby improving the accuracy of the hands-off judgment.

[0057] In an exemplary embodiment, determining the hands-off determination threshold according to wheel speed information includes:

[0058] Determine the vibration degree of the wheel according to the wheel speed information;

[0059] Determine a hands-off judgment threshold reference value according to the vibration degree of the wheel;

[0060] The hands-off determination threshold is determined according to the hands-off determination threshold reference value.

[0061] During the driving process, the wheels will vibrate due to the influence of the road surface flatness, which will cause the signal of the wheel speed sensor to be affected by the vibration. Therefore, according to the signal of the wheel speed sensor at different times, the vibration spectrum of the wheel can be obtained, that is, according to the wheel speed information, the vibration spectrum of the wheel can be obtained, and then the vibration degree of the wheel at different times can be determined.

[0062] The vibration degree of the wheel is closely related to the road surface flatness, and the size of the hands-off determination threshold is also closely related to the road surface flatness. Therefore, the vibration degree of the wheel and the hands-off determination threshold can also be associated accordingly, so that the hands-off determination threshold reference value can be determined by the vibration degree of the wheel, without first determining the specific conditions of the road surface flatness through the vibration degree of the wheel and then determining the hands-off determination threshold reference value based on the specific conditions of the road surface flatness. This simplifies the determination logic of the hands-off determination threshold reference value and simplifies the electronic control program.

[0063] The specific method of determining the degree of wheel vibration based on the signal of the wheel speed sensor is the same as the conventional method of determining the degree of vehicle body vibration using the signal of the acceleration sensor, and will not be described in detail here.

[0064] In an exemplary embodiment, determining the hands-off determination threshold according to the hands-off determination threshold reference value includes:

[0065] Determine whether the hands-off determination threshold reference value has lasted for a set period of time;

[0066] Based on the hands-off determination threshold reference value having been continuously valued for a set period of time, determining the hands-off determination threshold reference value as a new hands-off determination threshold value;

[0067] Since the hands-off determination threshold reference value has not been continuously set for a set period of time, the hands-off determination threshold determined last time is continuously used.

[0068] Since the signal change of the wheel speed sensor is not only affected by the flatness of the road surface, but also by other factors, such as passing through a manhole cover, speed bump or small stones, instantaneous vibration will cause the signal of the wheel speed sensor to change greatly instantaneously, which has nothing to do with the flatness of the road surface. However, the hands-off determination threshold reference value is determined to be the value when the road surface flatness is poor (i.e., the road condition is poor) due to the large degree of wheel vibration. If the hands-off determination threshold reference value is directly determined as the hands-off determination threshold, misjudgment will inevitably occur.

[0069] If the vibration is caused by the road surface condition, the wheel will continue to vibrate at a roughly equivalent level for a period of time. Therefore, the hands-off determination threshold reference value corresponding to the wheel vibration level will also continue for the set period of time, that is, remain unchanged for a period of time. At this time, the hands-off determination threshold reference value corresponds to the road surface flatness, so it is more reasonable to determine the hands-off determination threshold reference value as the new hands-off determination threshold.

[0070] If the hands-off determination threshold reference value does not last for the set time, it indicates that the wheel vibration is instantaneous vibration and is not caused by the road surface roughness. Therefore, it can be determined that the road surface roughness has not changed, the hands-off determination threshold remains unchanged, and the last determined hands-off determination threshold continues to be used.

[0071] In the factory state, the hands-off determination threshold can be set to the hands-off determination threshold reference value, which is the hands-off determination threshold under good road conditions. In subsequent use, the hands-off determination threshold can be adjusted according to changes in road surface flatness to improve the accuracy of hands-off determination.

[0072] In an exemplary embodiment, determining a hands-off determination threshold reference value according to the vibration level of the wheel includes:

[0073] Determining hands-off judgment threshold adjustment information according to the vibration degree of the wheel;

[0074] A hands-off determination threshold reference value is determined according to the hands-off determination threshold adjustment information.

[0075] The hands-off determination threshold can be adjusted in different ways as needed, such as by direct search or calculation. The calculation method can also be various, such as by addition or subtraction or by multiplication.

[0076] Therefore, firstly determine the hands-off determination threshold adjustment information according to the vibration degree of the wheel, and then determine the hands-off determination threshold reference value according to the hands-off determination threshold adjustment information. There can be a variety of implementation forms, which is convenient for reasonable selection according to needs.

[0077] In an exemplary embodiment, the hands-off determination threshold adjustment information is: an updated value of the hands-off determination threshold reference value; determining the hands-off determination threshold reference value based on the hands-off determination threshold adjustment information includes: determining the updated value of the hands-off determination threshold reference value as the hands-off determination threshold reference value.

[0078] When the hands-off determination threshold adjustment information is an updated value of the hands-off determination threshold reference value, the system does not need to calculate, and can directly determine the updated value of the hands-off determination threshold reference value as the hands-off determination threshold reference value. This solution can save the calculation steps, thereby simplifying the logic and simplifying the electronic control program.

[0079] In another exemplary embodiment, the hands-off determination threshold adjustment information is: a hands-off determination threshold reference value coefficient; determining the hands-off determination threshold reference value based on the hands-off determination threshold adjustment information includes: multiplying the hands-off determination threshold base value by the hands-off determination threshold reference value coefficient to determine the hands-off determination threshold reference value.

[0080] When the hands-off determination threshold adjustment information is the hands-off determination threshold reference value coefficient, the system can obtain the hands-off determination threshold reference value by simple multiplication calculation. Since the hands-off determination threshold reference value coefficient is usually relatively small, it is beneficial to reduce the requirement for system storage space.

[0081] In an exemplary embodiment, determining the hands-off determination threshold adjustment information according to the vibration degree of the wheel includes:

[0082] According to the mapping relationship between the vibration degree of the wheel and the hands-off determination threshold adjustment information, the hands-off determination threshold adjustment information corresponding to the vibration degree of the wheel is determined.

[0083] In this way, the mapping relationship between the vibration degree of the wheel and the hands-off determination threshold adjustment information can be directly stored in the system, and of course it can also be placed on the network, and the hands-off determination threshold adjustment information can be determined directly by searching.

[0084] In an exemplary embodiment, the mapping relationship between the vibration degree of the wheel and the hands-off determination threshold adjustment information is obtained by the corresponding relationship between the vibration degree of the wheel and the road surface roughness level and the corresponding relationship between the road surface roughness level and the hands-off determination threshold adjustment information.

[0085] Among them, the road surface roughness level is negatively correlated with the road surface roughness, the wheel vibration degree is negatively correlated with the road surface roughness, the hands-off judgment threshold reference value is positively correlated with the road surface roughness level, and the hands-off judgment threshold adjustment information is positively correlated with the hands-off judgment threshold reference value.

[0086] The road surface roughness grade is negatively correlated with the road surface roughness, which means: the higher the road surface roughness grade, the worse the road surface roughness and the worse the road surface condition; the lower the road surface roughness grade, the better the road surface roughness and the better the road surface condition. The wheel vibration degree is negatively correlated with the road surface roughness, which means: the more intense the wheel vibration degree, the worse the road surface roughness and the worse the road surface condition; the milder the wheel vibration degree, the better the road surface roughness and the better the road surface condition. Thus, the corresponding relationship between the wheel vibration degree and the road surface roughness grade can be obtained: the higher the road surface roughness grade, the more intense the wheel vibration degree; the lower the road surface roughness grade, the milder the wheel vibration degree.

[0087] The hands-off determination threshold reference value is positively correlated with the road surface smoothness level, which means: the higher the road surface smoothness level, the larger the hands-off determination threshold reference value; the lower the road surface smoothness level, the smaller the hands-off determination threshold reference value. The hands-off determination threshold adjustment information is positively correlated with the hands-off determination threshold reference value, which means: the larger the hands-off determination threshold reference value, the larger the hands-off determination threshold adjustment information; the smaller the hands-off determination threshold reference value, the smaller the hands-off determination threshold adjustment information. Thus, the corresponding relationship between the hands-off determination threshold adjustment information and the road surface smoothness level can be obtained: the higher the road surface smoothness level, the larger the hands-off determination threshold adjustment information; the lower the road surface smoothness level, the smaller the hands-off determination threshold adjustment information.

[0088] Therefore, the mapping relationship between the wheel vibration degree and the hands-off judgment threshold adjustment information can be obtained through the corresponding relationship between the wheel vibration degree and the road surface flatness level and the corresponding relationship between the road surface flatness level and the hands-off judgment threshold adjustment information. Specifically, the above mapping relationship can be established through experiments, experience summary, etc., and stored in the system, and of course, it can also be placed on the network.

[0089] In an exemplary embodiment, the road surface roughness level includes: level one, level two and level three, the road surface roughness of level one is better than the road surface roughness of level two, and the road surface roughness of level two is better than the road surface roughness of level three. The hands-off determination threshold adjustment information includes: first adjustment information, second adjustment information and third adjustment information, and the first adjustment information < second adjustment information < third adjustment information.

[0090] In the mapping relationship between the vibration degree of the wheel and the adjustment information of the hands-off determination threshold value:

[0091] When the vibration degree of the wheel is less than the first vibration degree, the hands-off determination threshold adjustment information is equal to the first adjustment information;

[0092] When the vibration degree of the wheel is greater than the first vibration degree and less than the second vibration degree, the hands-off determination threshold adjustment information is equal to the second adjustment information, and the second vibration degree is stronger than the first vibration degree;

[0093] When the vibration level of the wheel is greater than the second vibration level, the hands-off determination threshold adjustment information is equal to the third adjustment information.

[0094] This plan divides the road surface roughness into three levels: Level 1 has the best road surface roughness and is a good road; Level 2 has the second worst road surface roughness and is a slightly bad road; Level 3 has the worst road surface roughness and is a seriously bad road.

[0095] Correspondingly, the hands-off judgment threshold adjustment information is also divided into three levels: the first adjustment information corresponds to the first level road surface smoothness, the second adjustment information corresponds to the second level road surface smoothness, and the third adjustment information corresponds to the third level road surface smoothness.

[0096] Since the vibration degree of the wheel during driving cannot remain constant at the same value, the vibration degree of the wheel will fluctuate even under the same level of road surface roughness. Therefore, the vibration degree of the wheel can be divided into three intervals according to the road surface roughness level: when it is less than the first vibration degree, the road surface roughness level is level one, and the corresponding hands-off determination threshold adjustment information is the first adjustment information; when it is between the first and second vibration degrees, the road surface roughness level is level two, and the corresponding hands-off determination threshold adjustment information is the second adjustment information; when it is greater than the second vibration degree, the road surface roughness level is level three, and the corresponding hands-off determination threshold adjustment information is the third adjustment information.

[0097] For example, when the hands-off determination threshold adjustment information is an updated value of the hands-off determination threshold reference value, when the vibration degree of the wheel is less than the first vibration degree, the hands-off determination threshold reference value can be recorded as Kon; when the vibration degree of the wheel is between the first vibration degree and the second vibration degree, the hands-off determination threshold reference value can be recorded as Kon1; when the vibration degree of the wheel is greater than the second vibration degree, the hands-off determination threshold reference value can be recorded as Kon2, then Kon<Kon1<Kon2, such as Figure 4 shown.

[0098] The above division method can basically meet the usage requirements, and the electronic control program is relatively simple and uncomplicated.

[0099] Of course, the division method of road surface roughness level, wheel vibration degree, and hands-off judgment threshold adjustment information is not limited to the above method, and can also be divided into two levels, four levels or even more levels as needed.

[0100] In an exemplary embodiment, determining whether the driver has taken his hands off the steering wheel according to the hands-off determination threshold and the hand torque information includes:

[0101] comparing the hand torque information with a hands-off determination threshold;

[0102] It is determined whether the driver has taken his hands off the steering wheel based on the comparison result.

[0103] The judgment method of this scheme is simple and easy to implement.

[0104] In one example, determining whether the driver has taken their hands off the steering wheel based on the comparison result includes:

[0105] Based on the absolute value of the hand torque information being greater than the hands-off determination threshold, it is determined that the driver has not taken their hands off the steering wheel;

[0106] Based on the absolute value of the hand torque information being less than or equal to the hands-off determination threshold, it is determined that the driver has taken his hands off the steering wheel.

[0107] In an exemplary embodiment, determining the vibration degree of the wheel according to the wheel speed information includes:

[0108] Filtering the wheel speed information;

[0109] The vibration degree of the wheel is determined based on the result after filtering.

[0110] Filtering the wheel speed information, that is, filtering the signal of the wheel speed sensor, can filter out interference signals, which is beneficial to improving the accuracy of the subsequent judgment process.

[0111] In an exemplary embodiment, filtering the wheel speed information includes:

[0112] The wheel speed information is processed by low-pass filtering and high-pass filtering.

[0113] By setting the corresponding cutoff frequency during these two filtering processes, the excessively high and low frequencies are transitioned out, thereby filtering out the road surface frequency of bad roads, making it easier to accurately determine the degree of wheel vibration, and then accurately determine the hands-off judgment threshold corresponding to the road surface flatness level.

[0114] In one example, the wheel speed information is subjected to low-pass filtering and high-pass filtering in sequence, and the cutoff frequency of the low-pass filtering is higher than the cutoff frequency of the high-pass filtering.

[0115] In another example, the wheel speed information is processed sequentially by high-pass filtering and low-pass filtering, and the cutoff frequency of the high-pass filtering is lower than the cutoff frequency of the low-pass filtering.

[0116] Among them, the cutoff frequency of the low-pass filtering process and the cutoff frequency of the high-pass filtering process can be reasonably set according to the conventional road surface frequency.

[0117] In an exemplary embodiment, the wheel speed information is an average value of wheel speed information of a plurality of wheels of the vehicle.

[0118] This helps prevent a single wheel from passing over a manhole cover, small stones or other obstacles, which may lead to misjudgment of poor road conditions, and helps improve the accuracy of subsequent judgment processes.

[0119] As for which wheels' average wheel speed information to use, a reasonable selection can be made based on factors such as the vehicle's driving mode and the vehicle's specific structure.

[0120] In one example, the wheel speed information is an average of the wheel speed information of the left front wheel and the left rear wheel.

[0121] In another example, the wheel speed information is an average of the wheel speed information of the right front wheel and the right rear wheel.

[0122] In yet another example, the wheel speed information is an average of the wheel speed information of the left front wheel and the right front wheel.

[0123] In yet another example, the wheel speed information is an average of the wheel speed information of the left and right wheels and the right rear wheel.

[0124] like Figure 5 As shown, an embodiment of the present application further provides a driver hands-off detection device, including a processor and a memory storing a computer program, and when the processor executes the computer program, the steps of the driver hands-off detection method as described in any of the above embodiments are implemented.

[0125] The processor may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0126] The embodiment of the present application also provides a lane keeping method, including:

[0127] Determining whether the driver has taken his hands off the steering wheel according to any one of the above embodiments of the driver's hands-off detection method;

[0128] The lane keeping function is exited when the driver takes his hands off the steering wheel.

[0129] The lane keeping function continues as long as the driver does not take his hands off the steering wheel.

[0130] The lane keeping method provided in the embodiments of the present application adopts the driver hands-off detection method of any one of the above embodiments to determine whether the driver has taken his hands off the steering wheel, and thus has a high accuracy in hands-off determination. This is beneficial for avoiding frequent suppression of the lane keeping function due to misjudgment of hands-off, thereby improving the user experience, and is also beneficial for avoiding continued operation of the lane keeping function when the driver has taken his hands off the steering wheel due to misjudgment of hands-on, thereby improving user safety.

[0131] The embodiment of the present application further provides a lane keeping system, including: a hand torque detection device 410, a wheel speed detection device and a lane keeping control device 201 (ie, a LKS control device 201).

[0132] The hand torque detection device 410 is configured to detect the hand torque of the driver.

[0133] The wheel speed detection device is configured to detect the wheel speed.

[0134] The lane keeping control device 201 is configured to obtain wheel speed information and driver's hand torque information based on the detection results of the wheel speed detection device and the hand torque detection device 410, and determine whether the driver has taken his hands off the steering wheel based on the wheel speed information and the hand torque information, and control whether the lane keeping function is exited based on the detection results of the driver's hands-off detection module.

[0135] The lane keeping system provided by the embodiment of the present application can comprehensively combine the wheel speed information and the driver's hand torque information to determine whether the driver has taken his hands off the steering wheel. Therefore, the wheel speed information and the hand torque information can be used together as a basis for determining whether the driver has taken his hands off the steering wheel. Since the wheel speed information can reflect the vibration of the wheel, and thus indirectly reflect the flatness of the current road surface, in the process of determining whether the driver has taken his hands off the steering wheel, the flatness of the current road surface can be inferred based on the wheel speed information, and then the driver can be comprehensively determined based on the flatness of the current road surface and the driver's hand torque to determine whether the driver has taken his hands off. In this way, whether the driver has taken his hands off takes into account the driver's hand torque and the flatness of the current road surface, which is conducive to reducing the adverse effect of road surface flatness on determining whether the driver has taken his hands off the steering wheel, improving the accuracy of hands-off judgment, and thus improving user safety and user experience.

[0136] Moreover, compared with using an acceleration sensor to estimate the smoothness of the road surface, the embodiment of the present application estimates the smoothness of the current road surface through wheel speed information, that is, estimates the smoothness of the road surface through the signal of the wheel speed sensor. Since the acceleration sensor is mounted on the vehicle body and is relatively far from the ground, it will detect vehicle body vibrations other than steering wheel vibrations. As the sensor closest to the ground, the wheel speed sensor has a greater advantage than other sensors when used to monitor the road surface status, and is less affected by other factors, so it has a higher accuracy in estimating the road surface smoothness.

[0137] In addition, compared to inferring the road surface state through changes in the LKS steering control torque, this solution uses the signal of the wheel speed sensor to infer the road surface state. When the lane line recognition result is unstable or the road slope changes suddenly, the LKS steering control torque will still change significantly. Therefore, the change in the LKS steering control torque cannot accurately reflect the road surface state, and it is difficult to avoid misjudgment of hands-off. This solution uses the signal of the wheel speed sensor to infer the road surface state, which can eliminate the influence other than road surface excitation, thereby accurately inferring the road surface state and improving the accuracy of hands-off judgment.

[0138] The lane keeping control device 201 is also configured to obtain lane line information based on the detection results of the driving environment condition detection device, and determine the steering direction and steering control value based on the lane line information, so that the vehicle's steering system performs steering operations based on the steering direction and steering control value to keep the vehicle driving in the center of the lane.

[0139] Among them, Figure 6 As shown, the driving environment condition detection device 400 includes but is not limited to: a radar sensor 107, a camera sensor 108, a lidar sensor, an ultrasonic sensor, etc.

[0140] In one example, if Figure 7As shown, the driving environment condition detection device 400 includes: a first radar sensor 1071 for sensing the front driving environment, a second radar sensor 1072 for sensing the front right driving environment, a third radar sensor 1073 for sensing the front left driving environment, a first camera sensor 1081 mainly used to detect the front driving environment, a second camera sensor 1082 mainly used to detect the left driving environment of the vehicle, a third camera sensor 1083 mainly used to detect the right driving environment of the vehicle, a fourth radar sensor 1074 mainly used to detect the rear driving environment, a fifth radar sensor 1075 mainly used to detect the right rear driving environment, and a sixth radar sensor 1076 mainly used to detect the left rear driving environment.

[0141] As long as the driving environment can be detected, there is no requirement for the type of sensor (radar, laser radar, ultrasonic sensor, camera sensor 108, etc.). The sensor for detecting the driving environment can detect and identify the speed, relative speed, position, angle, size, etc. of three-dimensional objects around the vehicle.

[0142] Among them, as long as the driving environment ahead can be detected, the execution of the lane keeping function (LKS) can be guaranteed, and there is no requirement for the number of sensors.

[0143] The wheel speed detection device includes but is not limited to: a right front wheel speed sensor 112 , a left front wheel speed sensor 113 , a right rear wheel speed sensor 114 , and a left rear wheel speed sensor 115 .

[0144] In an exemplary embodiment, the lane keeping control device 201 includes a hands-off determination threshold determination module 2024 and a lane keeping control module 2011 (i.e., the LKS control module 2011). The hands-off determination threshold determination module 2024 is configured to determine the hands-off determination threshold according to wheel speed information. The lane keeping control module 2011 is configured to determine whether the driver has taken his hands off the steering wheel according to the hands-off determination threshold and hand torque information, and control whether the lane keeping function is exited according to the detection result of the driver's hands-off detection module.

[0145] In one example, the lane keeping control module 2011 is configured to: exit the lane keeping function based on the driver taking their hands off the steering wheel; and continue to execute the lane keeping function based on the driver not taking their hands off the steering wheel.

[0146] In one example, the lane keeping system further includes a driving environment condition detection device. The driving environment condition detection device is configured to detect driving environment conditions.

[0147] In an exemplary embodiment, the hands-off determination threshold determination module 2024 includes: a first determination unit, a second determination unit, and a third determination unit. The first determination unit is configured to determine the vibration degree of the wheel according to the wheel speed information. The second determination unit is configured to determine the hands-off determination threshold reference value according to the vibration degree of the wheel. The third determination unit is configured to determine the hands-off determination threshold according to the hands-off determination threshold reference value.

[0148] In an exemplary embodiment, the third determining unit is configured to:

[0149] Determine whether the hands-off determination threshold reference value has lasted for a set period of time;

[0150] Based on the hands-off determination threshold reference value having been continuously valued for a set period of time, determining the hands-off determination threshold reference value as a new hands-off determination threshold value;

[0151] Since the hands-off determination threshold reference value has not been continuously set for a set period of time, the hands-off determination threshold determined last time is continuously used.

[0152] In an exemplary embodiment, the second determination unit is configured to: determine hands-off determination threshold adjustment information according to the vibration degree of the wheel; and determine the hands-off determination threshold reference value according to the hands-off determination threshold adjustment information.

[0153] In an exemplary embodiment, the hands-off determination threshold adjustment information is: an updated value of the hands-off determination threshold reference value; and the second determination unit is configured to: determine the updated value of the hands-off determination threshold reference value as the hands-off determination threshold reference value.

[0154] In another exemplary embodiment, the hands-off determination threshold adjustment information is: the hands-off determination threshold reference value coefficient; the second determination unit is configured to: determine the product of the hands-off determination threshold base value and the hands-off determination threshold reference value coefficient as the hands-off determination threshold reference value.

[0155] In an exemplary embodiment, the second determination unit is configured to: determine the hands-off determination threshold adjustment information corresponding to the vibration degree of the wheel according to a mapping relationship between the vibration degree of the wheel and the hands-off determination threshold adjustment information.

[0156] In an exemplary embodiment, the mapping relationship between the vibration degree of the wheel and the hands-off determination threshold adjustment information is obtained by the corresponding relationship between the vibration degree of the wheel and the road surface roughness level and the corresponding relationship between the road surface roughness level and the hands-off determination threshold adjustment information.

[0157] Among them, the road surface roughness level is negatively correlated with the road surface roughness, the wheel vibration degree is negatively correlated with the road surface roughness, the hands-off judgment threshold reference value is positively correlated with the road surface roughness level, and the hands-off judgment threshold adjustment information is positively correlated with the hands-off judgment threshold reference value.

[0158] In an exemplary embodiment, the road surface flatness levels include: level one, level two and level three, the road surface flatness of level one is better than that of level two, and the road surface flatness of level two is better than that of level three; the hands-off determination threshold adjustment information includes: first adjustment information, second adjustment information and third adjustment information, the first adjustment information < second adjustment information < third adjustment information.

[0159] In the mapping relationship between the vibration degree of the wheel and the adjustment information of the hands-off determination threshold value:

[0160] When the vibration degree of the wheel is less than the first vibration degree, the hands-off determination threshold adjustment information is equal to the first adjustment information;

[0161] When the vibration degree of the wheel is greater than the first vibration degree and less than the second vibration degree, the hands-off determination threshold adjustment information is equal to the second adjustment information;

[0162] When the vibration level of the wheel is greater than the second vibration level, the hands-off determination threshold adjustment information is equal to the third adjustment information.

[0163] In an exemplary embodiment, the lane keeping control module 2011 is configured to: compare the hand torque information with a hands-off determination threshold; and determine whether the driver has taken his hands off the steering wheel based on the comparison result.

[0164] In one example, the second determination unit is configured to: determine that the driver has not taken their hands off the steering wheel based on the absolute value of the hand torque information being greater than a hands-off determination threshold; determine that the driver has taken their hands off the steering wheel based on the absolute value of the hand torque information being less than or equal to the hands-off determination threshold.

[0165] In an exemplary embodiment, the lane keeping system further includes a filtering module, and the filtering module is configured to: filter the wheel speed information; and determine the vibration degree of the wheel according to the result of the filtering process.

[0166] In an exemplary embodiment, the filtering module includes a low-pass filtering processing module 2021 (i.e., LPF processing module 2021) and a high-pass filtering processing module 2022 (i.e., HPF processing module 2022). The low-pass processing module performs low-pass filtering on the wheel speed information, and the high-pass processing module performs high-pass filtering on the wheel speed information.

[0167] In an exemplary embodiment, the wheel speed information is an average of wheel speed information of multiple wheels of the vehicle. The lane keeping system further includes a calculation module 2023, which is configured to calculate an average of wheel train information of multiple wheels.

[0168] like Figure 6As shown, an embodiment of the present application further provides a vehicle, including a driving assistance ECU 200 (i.e., a driving assistance control device), and the driving assistance ECU 200 includes a lane keeping control device 201 of any one of the above embodiments, and thus has all the above beneficial effects, which will not be repeated here.

[0169] Among them, the vehicle also includes a signal input system, a signal output system and an execution system.

[0170] like Figure 6 As shown, the signal input system is configured to input a signal to the lane keeping control device 201 of the auxiliary driving system. The signal output system is configured to receive an output signal of the lane keeping control device 201 and control the execution system to perform a corresponding operation according to the output signal.

[0171] Among them, Figure 6 As shown, the signal input system may include: a turn signal switch 101 capable of detecting the driver's turn signal operation, an accelerator pedal sensor 102 for detecting the driver's throttle operation, a brake pedal sensor 103 for detecting the driver's brake operation, a steering angle sensor 104 for detecting the driver's steering operation, a hand torque sensor 105 for detecting the driver's steering operation force, a vehicle speed sensor 106 for detecting the vehicle speed, a yaw rate sensor 109 for detecting the vehicle's motion state, a longitudinal acceleration sensor 110, a lateral acceleration sensor 111, and a wheel speed detection device (including a right front wheel speed sensor 112, a left front wheel speed sensor 113, a right rear wheel speed sensor 114, and left and right wheel speed sensors 115) and a driving environment condition detection device 400 (such as a camera sensor 108 and a radar sensor 107 for detecting the surrounding environment).

[0172] The signal output system may include: an engine ECU 301 , a brake ECU 302 , a steering ECU 303 , and an information display ECU 304 .

[0173] The execution system may include: an engine 311, a brake system 312, a steering system 313 and an information display device 314. The engine ECU 301 controls the engine 311 according to the output signal, and mainly performs acceleration control. The brake ECU 302 controls the brake system 312, and mainly performs deceleration control. The steering ECU 303 controls the steering system 313, and mainly performs lateral steering control. The information display ECU 304 controls the information display device 314, and mainly provides the driver with the display of vehicle status and function control status information.

[0174] In a specific embodiment, the wheel speed information is the average of the wheel speed information of the right front wheel and the right rear wheel. Figure 8As shown, the detection signals of the right front wheel speed sensor and the left front wheel speed sensor are added and averaged by the calculation module 2023, and then processed by the low-pass filter processing module 2021 and the high-pass filter processing module 2022 and sent to the hands-off determination threshold determination module 2024. The hands-off determination threshold determination module 2024 determines the hands-off determination threshold and sends it to the lane keeping control module 2011. The detection results of the driving environment condition detection device (such as a camera sensor) and the hand torque detection device 410 are also sent to the lane keeping control module 2011. The lane keeping control module 2011 determines whether the driver has taken his hands off the steering wheel based on the comparison result of the hands-off determination threshold and the hand torque; when it is determined that the driver has taken his hands off the steering wheel, the lane keeping function is exited; when it is determined that the driver has not taken his hands off the steering wheel, the steering direction and the steering control value (such as the steering request torque / steering request angle) are determined based on the detection result of the driving environment condition detection device, and sent to the steering ECU 303, so that the steering system 313 performs the steering operation to keep the vehicle driving in the center of the lane.

[0175] The technical effects of the above embodiments can be understood by referring to the embodiments of the aforementioned driver's hands-off detection method, which will not be repeated here.

[0176] In summary, the driver hands-off detection method and device, lane keeping method and system provided in the embodiments of the present application can infer the flatness of the current road surface based on the wheel speed information, and then reasonably determine the hands-off judgment threshold according to different road conditions, thereby improving the accuracy of the hands-off judgment and improving the safety and user experience of the LKS function.

[0177] In any one or more of the above exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored on or transmitted via a computer-readable medium as one or more instructions or codes, and executed by a hardware-based processing unit. A computer-readable medium may include a computer-readable storage medium corresponding to a tangible medium such as a data storage medium, or a communication medium that facilitates the transmission of a computer program from one place to another, such as according to a communication protocol. In this way, a computer-readable medium may generally correspond to a non-temporary tangible computer-readable storage medium or a communication medium such as a signal or carrier wave. A data storage medium may be any available medium that can be accessed by one or more computers or one or more processors to retrieve instructions, codes, and / or data structures for implementing the technology described in the present disclosure. A computer program product may include a computer-readable medium.

[0178] By way of example and not limitation, such computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage, flash memory, or any other medium that can be used to store the desired program code in the form of instructions or data structures and can be accessed by a computer. Moreover, any connection may also be referred to as a computer-readable medium. For example, if instructions are transmitted from a website, server or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio and microwave are included in the definition of medium. However, it should be understood that computer-readable storage media and data storage media do not include connections, carrier waves, signals, or other transient (transient) media, but are directed to non-transient tangible storage media. As used herein, disks and optical disks include compact disks (CDs), laser disks, optical disks, digital versatile disks (DVDs), floppy disks, or Blu-ray disks, etc., where disks typically reproduce data magnetically, while optical disks use lasers to reproduce data optically. Combinations of the above should also be included within the scope of computer-readable media.

[0179] For example, instructions may be executed by one or more processors such as one or more digital signal processors (DSPs), general purpose microprocessors, application specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Thus, the term "processor" as used herein may refer to any of the above structures or any other structures suitable for implementing the techniques described herein. Additionally, in some aspects, the functionality described herein may be provided within dedicated hardware and / or software modules configured for encoding and decoding, or incorporated in a combined codec. Also, the techniques may be fully implemented in one or more circuits or logic elements.

[0180] The technical solutions of the embodiments of the present disclosure can be implemented in a wide variety of devices or equipment, including wireless mobile phones, integrated circuits (ICs) or a group of ICs (e.g., chipsets). Various components, modules or units are described in the embodiments of the present disclosure to emphasize the functional aspects of the devices configured to perform the described techniques, but they do not necessarily need to be implemented by different hardware units. Instead, as described above, the various units can be combined in a codec hardware unit or provided by a collection of interoperable hardware units (including one or more processors as described above) in combination with suitable software and / or firmware.

Claims

1. A method for detecting a driver's hands-off behavior, characterized in that: include: Obtain wheel speed information and driver's hand torque information; determining a vibration degree of the wheel according to the wheel speed information; Determining hands-off judgment threshold adjustment information according to the vibration degree of the wheel; determining a hands-off determination threshold reference value according to the hands-off determination threshold adjustment information; Determining a hands-off determination threshold according to the hands-off determination threshold reference value; determining whether the driver has taken his hands off the steering wheel according to the hands-off determination threshold and the hand torque information; Among them, the hands-off determination threshold adjustment information is: the updated value of the hands-off determination threshold reference value; the determination of the hands-off determination threshold reference value based on the hands-off determination threshold adjustment information includes: determining the updated value of the hands-off determination threshold reference value as the hands-off determination threshold reference value; or, the hands-off determination threshold adjustment information is: the hands-off determination threshold reference value coefficient; the determination of the hands-off determination threshold reference value based on the hands-off determination threshold adjustment information includes: determining the product of the hands-off determination threshold base value and the hands-off determination threshold reference value coefficient as the hands-off determination threshold reference value.

2. The method for detecting a driver's hands-off behavior according to claim 1, characterized in that: The step of determining the hands-off determination threshold according to the hands-off determination threshold reference value comprises: Determining whether the hands-off determination threshold reference value has been maintained for a set time period; Based on the fact that the hands-off determination threshold reference value has been continuously set for a period of time, determining the hands-off determination threshold reference value as a new hands-off determination threshold value; Based on the fact that the hands-off determination threshold reference value does not continue to be set for a period of time, the hands-off determination threshold determined last time is continuously used.

3. The method for detecting a driver's hands-off behavior according to claim 1, characterized in that: The step of determining the hands-off determination threshold adjustment information according to the vibration degree of the wheel includes: According to the mapping relationship between the vibration degree of the wheel and the hands-off determination threshold adjustment information, the hands-off determination threshold adjustment information corresponding to the vibration degree of the wheel is determined.

4. The method for detecting a driver's hands-off behavior according to claim 3, characterized in that: The mapping relationship between the vibration degree of the wheel and the hands-off determination threshold adjustment information is obtained from the corresponding relationship between the vibration degree of the wheel and the road surface roughness grade and the corresponding relationship between the road surface roughness grade and the hands-off determination threshold adjustment information; Among them, the road surface roughness level is negatively correlated with the road surface roughness, the wheel vibration level is negatively correlated with the road surface roughness, the hands-off determination threshold reference value is positively correlated with the road surface roughness level, and the hands-off determination threshold adjustment information is positively correlated with the hands-off determination threshold reference value.

5. The method for detecting a driver's hands-off behavior according to claim 4, characterized in that: The road surface flatness level includes: level one, level two and level three, the road surface flatness of level one is better than the road surface flatness of level two, and the road surface flatness of level two is better than the road surface flatness of level three; the hands-off determination threshold adjustment information includes: first adjustment information, second adjustment information and third adjustment information, the first adjustment information<the second adjustment information<the third adjustment information; In the mapping relationship between the vibration degree of the wheel and the hands-off determination threshold adjustment information: When the vibration degree of the wheel is less than the first vibration degree, the hands-off determination threshold adjustment information is equal to the first adjustment information; When the vibration degree of the wheel is greater than the first vibration degree and less than the second vibration degree, the hands-off determination threshold adjustment information is equal to the second adjustment information, and the second vibration degree is stronger than the first vibration degree; When the vibration level of the wheel is greater than the second vibration level, the hands-off determination threshold adjustment information is equal to third adjustment information.

6. The method for detecting a driver's hands-off behavior according to any one of claims 1 to 5, characterized in that: The determining whether the driver has taken his hands off the steering wheel according to the hands-off determination threshold and the hand torque information comprises: comparing the hand torque information with the hands-off determination threshold; It is determined whether the driver has taken his hands off the steering wheel based on the comparison result.

7. The method for detecting a driver's hands-off behavior according to any one of claims 1 to 5, characterized in that: Determining the vibration degree of the wheel according to the wheel speed information includes: Performing filtering processing on the wheel speed information; The vibration degree of the wheel is determined according to the result after filtering. 8 . The method for detecting a hands-off driver's driving according to claim 1 , wherein the wheel speed information is an average of wheel speed information of a plurality of wheels of the vehicle.

9. A driver's hands-off detection device, characterized in that: The device comprises a processor and a memory storing a computer program, wherein when the processor executes the computer program, the steps of the driver's hands-off detection method as claimed in any one of claims 1 to 8 are implemented.

10. A lane keeping method, characterized in that: include: The driver's hands-off detection method according to any one of claims 1 to 8, determining whether the driver has taken his hands off the steering wheel; The lane keeping function is exited when the driver takes his hands off the steering wheel.

11. A lane keeping system, characterized in that: include: A hand torque detection device, configured to detect the driver's hand torque; A wheel speed detection device, configured to detect the wheel speed; a lane keeping control device, configured to: acquire wheel speed information and driver's hand torque information according to detection results of the wheel speed detection device and the hand torque detection device, determine a wheel vibration degree according to the wheel speed information, determine hands-off determination threshold adjustment information according to the wheel vibration degree, determine a hands-off determination threshold reference value according to the hands-off determination threshold adjustment information, determine a hands-off determination threshold according to the hands-off determination threshold reference value, determine whether the driver has taken his hands off the steering wheel according to the hands-off determination threshold and the hand torque information, and control whether the lane keeping function is exited according to the determination result of whether the driver has taken his hands off the steering wheel; Among them, the hands-off determination threshold adjustment information is: the updated value of the hands-off determination threshold reference value; the determination of the hands-off determination threshold reference value based on the hands-off determination threshold adjustment information includes: determining the updated value of the hands-off determination threshold reference value as the hands-off determination threshold reference value; or, the hands-off determination threshold adjustment information is: the hands-off determination threshold reference value coefficient; the determination of the hands-off determination threshold reference value based on the hands-off determination threshold adjustment information includes: determining the product of the hands-off determination threshold base value and the hands-off determination threshold reference value coefficient as the hands-off determination threshold reference value.

Images