Automatic driving system intervention method based on driver status

Abstract

The present invention discloses a method for intervening in an automatic driving system based on the driver's state. The main design concept of the present invention is to collect the driver's driving behavior data and physiological data in real time during vehicle driving, and continuously score these two types of data to obtain a multidimensional quantitative score that characterizes the driver's current state. Then, in combination with the vehicle's operating conditions, based on the multidimensional quantitative score and its weight, several target quantitative scores are selected and compared with the score threshold to determine the degree levels that characterize various driver conditions; according to the number of each degree level, the automatic driving system is automatically turned on to take over the driver's vehicle driving control. The present invention scores and grades the degree of user emergency situations, and decides the timing of active automatic driving intervention based on the number of each degree level, which can form a seamless takeover effect in the driver's emergency situation and significantly reduce the probability of traffic accidents caused by the driver's sudden condition.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method for intervening in an autonomous driving system based on driver status. Background Art

[0002] With the continuous development of science and technology, autonomous driving algorithms and application solutions are becoming more and more mature. However, at this stage, most users trust their own driving control skills more than algorithm-controlled vehicles.

[0003] However, in the actual driving process, drivers will inevitably encounter some emergency situations, such as sudden illness, interference, injury, etc., which will cause the user to be unable to maintain a good driving state. At this time, the automatic driving system needs to actively intervene to avoid traffic accidents caused by the driver's inability to drive the vehicle normally.

[0004] At present, users mostly switch to automatic driving mode through physical buttons or voice commands. On the one hand, the triggering of the above-mentioned switching to automatic driving intervention requires the user to be in normal driving status, and for some emergency situations, the user cannot actively trigger the switching operation; on the other hand, in some emergency scenarios, it is difficult for users to take care of the switching operation, that is, there is not enough time for users to think about using the automatic driving function to take over driving the vehicle, which can easily lead to traffic accidents. Summary of the Invention

[0005] In view of the above, the present invention aims to provide an automatic driving system intervention method based on the driver's status, so that manual driving can be switched to automatic driving mode naturally and seamlessly, avoiding the problem of the user still having to actively control or take into account the switching of driving modes in an emergency situation.

[0006] The technical solution adopted in the present invention is as follows:

[0007] The present invention provides a method for intervening in an automatic driving system based on a driver's state, comprising:

[0008] During vehicle driving, real-time collection of the driver's driving behavior data and physiological data. The driving behavior data includes at least the duration of head turns exceeding a preset angle and the duration of hands being off the steering wheel. The physiological data is used to characterize the driver's current health and mental state.

[0009] Continuously scoring the driving behavior data and the physiological data to obtain a multidimensional quantitative score representing the driver's current state;

[0010] In combination with the vehicle operating conditions, based on the multi-dimensional quantitative scores and their weights, several target quantitative scores are selected and compared with predetermined corresponding score thresholds to determine the severity levels of the driver's current various conditions;

[0011] Depending on the number of levels, the autonomous driving system is automatically turned on to take over the vehicle driving control from the driver.

[0012] In at least one possible implementation, the continuously scoring the driving behavior data and the physiological data includes:

[0013] Determining a first score and weight corresponding to the duration of the head turning, a second score and weight corresponding to the duration of one hand off the steering wheel, a third score and weight corresponding to the duration of both hands off the steering wheel, and a fourth score and weight corresponding to the physiological state represented by the physiological data;

[0014] In the vehicle forward driving condition, the fourth score weight ≥ the first score weight > the third score weight > the second score weight;

[0015] In the vehicle reversing condition, the fourth score weight ≥ the third score weight > the second score weight > the first score weight.

[0016] In at least one possible implementation, determining the degree of the driver's current multiple situations includes:

[0017] When the vehicle is moving forward, the fourth score and the first score are selected first, and the levels of the current fourth score and the first score are determined according to the score thresholds obtained with the corresponding weights; then the third score or the second score is selected, and the levels of the current third score or the second score are determined according to the score thresholds obtained with the corresponding weights.

[0018] In at least one possible implementation, determining the degree of the driver's current multiple situations includes:

[0019] In the vehicle reversing condition, only the fourth score and the third score are selected, and the levels of the current fourth score and the third score are determined according to the score thresholds obtained according to the corresponding weights.

[0020] In at least one possible implementation, the intervention method further includes: after the autonomous driving system takes over the vehicle, deciding to go to a predetermined destination or navigate to a nearby permitted parking area based on the number of each level.

[0021] In at least one possible implementation, the intervention method further includes: after the autonomous driving system takes over the vehicle, within a preset time threshold, based on the changes in the number of each degree level, deciding whether to send an assistance request to the established platform and navigate to a preset assistance location.

[0022] In at least one possible implementation, the intervention method further includes: after the autonomous driving system takes over the vehicle, only manual exit from the autonomous driving system is allowed.

[0023] Compared with existing technologies, the main design concept of the present invention is to collect the driver's driving behavior data and physiological data in real time during vehicle driving, and continuously score these two types of data to obtain a multidimensional quantitative score that represents the driver's current state. Then, based on the multidimensional quantitative score and its weight, a number of target quantitative scores are selected and compared with the score thresholds in combination with the vehicle's operating conditions to determine the degree of each driver's various conditions. Based on the number of degree levels, the autonomous driving system is automatically activated to take over the driver's driving control. The present invention scores and grades the degree of user emergency situations, and determines the timing of active autonomous driving intervention based on the number of degree levels. This can achieve a seamless takeover effect in driver emergency situations, significantly reducing the probability of traffic accidents caused by driver emergencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described below with reference to the accompanying drawings, in which:

[0025] Figure 1 A schematic diagram of an automatic driving system intervention method based on driver status provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0027] The present invention proposes an embodiment of an automatic driving system intervention method based on the driver's state. Specifically, Figure 1 shown, including:

[0028] Step S1: During vehicle driving, real-time driving behavior data and physiological data of the driver are collected. The driving behavior data includes at least the duration of head turning exceeding a preset angle and the duration of hands being off the steering wheel. The physiological data is used to characterize the driver's current health and mental state.

[0029] The aforementioned collection and implementation of driving behavior data and physiological data can be implemented by, but is not limited to, various mature collection technologies such as image, sound, and tactile sensations, which will not be elaborated here. However, it should be noted that in this embodiment, the emphasis on the duration of head turning exceeding a preset angle and the duration of hands being off the steering wheel without contact is to measure whether the current situation is a special one from the perspective of driving operation, such as an emergency in the rear of the vehicle, forcing the driver to turn his head to check for a response, or to take his hands off the steering wheel to deal with it. Both durations can be calibrated as needed in milliseconds, and the head turning angle threshold involved can be pre-set to, for example, a sector-shaped field of view for normal driving. If the preset angle is exceeded, it can be considered that the driver's field of view cannot take into account the area in front of the vehicle.

[0030] Regarding the physiological data, it may include features such as facial expressions, breathing, heart rate, eye contact, breath, and head drooping that characterize the driver's physiological condition. The present invention does not limit this. It can be pointed out that when the present invention subsequently examines this dimension, it can be refined into multiple physiological characteristics separately, or it can integrate multiple physiological characteristics to obtain a comprehensive examination indicator.

[0031] Step S2: continuously scoring the driving behavior data and the physiological data to obtain a multidimensional quantitative score representing the driver's current state;

[0032] For this scoring strategy, different methods can be designed in actual operation. Here are the following preferred implementation methods for reference:

[0033] Determining a first score and weight corresponding to the duration of the head turn, a second score and weight corresponding to the duration of one-handed-off-the-steering-wheel, a third score and weight corresponding to the duration of both-handed-off-the-steering-wheel, and a fourth score and weight corresponding to the physiological state represented by the physiological data (as mentioned above, in some embodiments, the fourth score may be a plurality of refined sub-scores, or a comprehensive score obtained by fusing several sub-branches);

[0034] And when the vehicle is moving forward, the fourth score weight ≥ the first score weight > the third score weight > the second score weight; when the vehicle is reversing, the fourth score weight ≥ the third score weight > the second score weight > the first score weight.

[0035] In actual application, the five-point system, the ten-point system, and the one-hundred-point system can be adjusted as needed, and this embodiment does not limit this.

[0036] Step S3: In combination with the vehicle operating conditions, based on the multi-dimensional quantitative scores and their weights, several target quantitative scores are selected and compared with predetermined corresponding score thresholds to determine the degree of the driver's current various conditions;

[0037] This can be expanded into the following specific examples in some embodiments:

[0038] Under the vehicle's forward driving condition, the fourth score and the first score are preferentially selected, and the levels of the current fourth score and the first score are determined according to the score thresholds obtained with the corresponding weights, for example, the fourth score or the first score is determined to be one of the three preset levels of mild, moderate, and severe; then the third score or the second score is selected, and the level of the current third score or the second score is determined according to the score thresholds obtained with the corresponding weights, for example, the third score or the second score is determined to be one of the three preset levels of mild, moderate, and severe.

[0039] In the vehicle reversing condition, it is preferable to select only the fourth score and the third score, and determine the level of the current fourth score and the third score according to the score threshold obtained by the corresponding weight, for example, determining that the fourth score or the third score is one of the three preset levels of mild, moderate, and severe.

[0040] Step S4: Automatically start the automatic driving system according to the number of each level to take over the vehicle driving control from the driver.

[0041] This process can set the quantitative values ​​of each level that triggers automatic driving intervention as needed. For example, when it is determined that there are two moderate levels or at least one severe level, the driving mode is automatically switched without prompting the driver to switch manually. Of course, the present invention does not exclude the possibility that in actual application, if only one moderate level appears and the others are mild, the driver can be asked by voice whether he needs to connect to the assisted driving system at present. The present invention does not limit the quantitative value and the way of asking the driver.

[0042] It should also be pointed out here that after the autonomous driving system takes over the vehicle, it can decide whether to go to the predetermined destination or navigate to the nearest permitted parking area based on the number of each level. Based on this, after the autonomous driving system takes over the vehicle, it can also decide whether to send an assistance request to the established platform and navigate to the preset assistance location based on the changes in the number of each level within a preset time threshold. The platforms here can be diverse, such as the Internet of Vehicles platform, vehicle management platform, traffic police platform, first aid platform, rescue platform, etc. For example, if the number of each level in the triggering stage does not change within a certain period of time or the number of moderate / severe situations increases, the autonomous driving system communicates with the Internet of Vehicles platform and issues an auxiliary processing request or alarm information.

[0043] Finally, it can be added that after the autonomous driving system takes over the vehicle, only manual exit from the autonomous driving function is allowed, such as restoring manual driving mode through user operation of physical buttons or voice commands. Even if the continuous analysis results show that the urgency has decreased, autonomous driving can be exited without the user's manual judgment, and the intelligent system must not be automatically exited. This is to avoid the actual emergency situation from being reliably eliminated. If the system mistakenly switches to manual driving at this time, it may bring subsequent risks.

[0044] In summary, the main design concept of the present invention is to collect the driver's driving behavior data and physiological data in real time during vehicle driving, and continuously score these two types of data to obtain a multidimensional quantitative score that represents the driver's current state. Then, based on the vehicle's operating conditions, several target quantitative scores are selected based on the multidimensional quantitative score and its weights and compared with the score threshold to determine the degree of each driver's various conditions. Based on the number of each degree level, the automatic driving system is automatically activated to take over the driver's driving control. The present invention scores and grades the degree of user emergency situations, and determines the timing of active automatic driving intervention based on the number of each degree level. This can achieve a seamless takeover effect in the driver's emergency situation, significantly reducing the probability of traffic accidents caused by driver emergencies.

[0045] In the embodiment of the present invention, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a, b and c, where a, b, c can be single or multiple.

[0046] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings, but the above is only a preferred embodiment of the present invention. It should be noted that the technical features involved in the above embodiments and their preferred modes can be reasonably combined and matched into a variety of equivalent schemes by those skilled in the art without departing from or changing the design ideas and technical effects of the present invention; therefore, the scope of implementation of the present invention is not limited to what is shown in the drawings. Any changes made in accordance with the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the description and drawings, should be within the scope of protection of the present invention.

Claims

1. A method for intervening in an automatic driving system based on a driver's state, characterized in that: include: During vehicle driving, real-time collection of the driver's driving behavior data and physiological data. The driving behavior data includes at least the duration of head turns exceeding a preset angle and the duration of hands being off the steering wheel. The physiological data is used to characterize the driver's current health and mental state. The driving behavior data and the physiological data are continuously scored to obtain a multidimensional quantitative score representing the driver's current state, including: determining a first score and weight corresponding to the duration of head turning, a second score and weight corresponding to the duration of one-handed off the steering wheel, a third score and weight corresponding to the duration of both hands off the steering wheel, and a fourth score and weight corresponding to the physiological state represented by the physiological data; in a forward vehicle operation condition, the fourth score weight ≥ the first score weight > the third score weight > the second score weight; in a reverse vehicle operation condition, the fourth score weight ≥ the third score weight > the second score weight > the first score weight; In combination with the vehicle operating conditions, based on the multi-dimensional quantitative scores and their weights, several target quantitative scores are selected and compared with predetermined corresponding score thresholds to determine the degree of the driver's current multiple conditions, including: in the vehicle forward operating condition, the fourth score and the first score are preferentially selected, and the current level of the fourth score and the first score is determined according to the score threshold obtained by the corresponding weight; then the third score or the second score is selected, and the current level of the third score or the second score is determined according to the score threshold obtained by the corresponding weight; Depending on the number of levels, the autonomous driving system is automatically turned on to take over the vehicle driving control from the driver.

2. The method for automatic driving system intervention based on driver status according to claim 1, characterized in that: The degree of determining the driver's current multiple situations includes: In the vehicle reversing condition, only the fourth score and the third score are selected, and the levels of the current fourth score and the third score are determined according to the score thresholds obtained according to the corresponding weights.

3. The method for automatic driving system intervention based on driver status according to claim 1, characterized in that: The intervention method also includes: after the autonomous driving system takes over the vehicle, deciding to go to a predetermined destination or navigate to a nearby permitted parking area based on the number of each degree level.

4. The method for automatic driving system intervention based on driver status according to claim 1, characterized in that: The intervention method also includes: after the autonomous driving system takes over the vehicle, within a preset time threshold, based on the changes in the number of each degree level, deciding whether to send an assistance request to the established platform and navigate to a preset assistance location.

5. The method for intervening in an automatic driving system based on driver status according to any one of claims 1 to 4, characterized in that: The intervention method also includes: after the autonomous driving system takes over the vehicle, only manual exit from the autonomous driving system is allowed.

Images