WO2023122913A1 - 一种智能驾驶方法、系统和装置 - Google Patents

一种智能驾驶方法、系统和装置 Download PDF

Info

Publication number
WO2023122913A1
WO2023122913A1 PCT/CN2021/141791 CN2021141791W WO2023122913A1 WO 2023122913 A1 WO2023122913 A1 WO 2023122913A1 CN 2021141791 W CN2021141791 W CN 2021141791W WO 2023122913 A1 WO2023122913 A1 WO 2023122913A1
Authority
WO
WIPO (PCT)
Prior art keywords
driver
reminder
parameter set
reminders
fatigued
Prior art date
Application number
PCT/CN2021/141791
Other languages
English (en)
French (fr)
Inventor
何曙亮
卢远志
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to PCT/CN2021/141791 priority Critical patent/WO2023122913A1/zh
Publication of WO2023122913A1 publication Critical patent/WO2023122913A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/04—Monitoring the functioning of the control system
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • B60W50/16—Tactile feedback to the driver, e.g. vibration or force feedback to the driver on the steering wheel or the accelerator pedal
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot

Definitions

  • the present application relates to the technical field of intelligent driving, in particular to an intelligent driving method, system and device.
  • the state of the driver is very important.
  • the International Society of Automatic Machine Engineers divides the automatic driving technology into six levels from L0 to L5.
  • the driver In the automatic driving technology of L2 level and below, the driver is still in the dominant position of the vehicle, and the driver needs to pay attention to the vehicle and the surrounding environment in real time. environment.
  • L3 level and above automatic driving technology the automatic driving system is in a dominant position over the vehicle, but the driver may need to take over the vehicle under special circumstances. It can be seen that during the driving process of the vehicle, if the driver's condition is poor, such as fatigue, it is very likely that the driver will not be able to respond when the vehicle sends out a reminder, and a safety accident will occur.
  • the present application provides an intelligent driving method, system and device, in order to reduce the risk of safety accidents and improve safety.
  • the present application provides an intelligent driving method, which can be executed by an intelligent driving device, or can also be executed by components (such as chips, chip systems, etc.) configured in the intelligent driving device, or can also be It is realized by a logic module or software capable of realizing all or part of the functions of the intelligent driving device, which is not limited in this application.
  • the method includes: obtaining a first parameter set, the first parameter set including one or more of the following: respiratory rate, blood oxygen saturation and heart rate; based on the first parameter set, predicting whether the driver is fatigued ; In the case of predicting that the driver will be fatigued, a reminder is issued to remind the driver to pay attention to the driving situation of the vehicle.
  • the application predicts whether the driver will be fatigued by using one or more of the above-mentioned parameters obtained, that is, Determines if the driver will be fatigued next, and alerts the driver if he will. That is, before the driver is tired, a reminder is sent to the driver, so that the driver pays attention to the driving situation of the vehicle, thereby reducing the risk of safety accidents and improving safety.
  • predicting whether the driver is fatigued based on the first parameter set includes: when the first parameter set satisfies the first preset condition, predicting Drivers will be fatigued.
  • the driver when the first parameter set satisfies the first preset condition, it is judged that the driver will be fatigued, and a specific implementation method for predicting whether the driver is fatigued according to the first parameter set is given, so as to predict whether the driver will be fatigued.
  • the driver When the driver will be fatigued, the driver will be reminded in advance, which is beneficial to improve the safety of the driver.
  • a possible design is that the first parameter set includes a respiratory rate, and the first preset condition includes: the respiratory rate is less than a first preset value.
  • the first parameter set includes blood oxygen saturation, and the first preset condition includes: blood oxygen saturation is less than a second preset value.
  • the first parameter set includes heart rate, and the first preset condition includes: the heart rate is smaller than a third preset value.
  • each parameter in the first parameter set can correspond to a preset value, and when one or more parameters in the first parameter set are less than the corresponding preset value, it can be determined that the driver will be fatigued , so as to remind the driver in advance, which is conducive to reducing the risk of safety accidents and improving the safety of the driver.
  • a reminder when the driver is predicted to be fatigued, a reminder is issued, including: when the driver is predicted to be fatigued, how many Reminders are issued.
  • the types of reminders include one or more of the following: visual reminders, auditory reminders, and tactile reminders.
  • the intelligent driving device can select any one or more types of reminders for reminders.
  • the flexibility of reminders is improved, and it is beneficial for drivers to receive vehicle information in a timely manner. remind. For example, if the driver's eyes are not looking ahead, the visual reminder may not be effective. You can choose auditory reminder or tactile reminder, or even choose auditory reminder and tactile reminder to ensure that the driver can receive the reminder from the vehicle.
  • multiple reminders are issued, including: when the driver is predicted to be fatigued , to issue the first reminder, the type of the first reminder includes one of visual reminder, auditory reminder and tactile reminder; in the case of no response from the driver is detected, a second reminder is sent, the type of the second reminder includes visual reminder, Two of auditory reminders and tactile reminders; when no response from the driver is detected, a third reminder is issued, and the types of the third reminder include visual reminders, auditory reminders and tactile reminders.
  • the first parameter set further includes the driver's historical driving habits and/or image information collected by the camera; and the method further includes: Habitual and/or graphic information to determine the type of first reminder.
  • the type of the first reminder is determined by further combining the driver's historical driving habits and/or image information collected by the camera. For example, the driver is currently in a state of not paying attention to the vehicle, the driver's historical driving habits indicate that the driver's ability to take over the vehicle is weak, and the driver is predicted to be fatigued through the first parameter, then the intensity of the first reminder can be Stronger, like visual and audible alerts for the first time.
  • the type of reminder can be more reasonably determined, which is beneficial for the driver to receive the reminder in a more timely manner and improves safety.
  • the method further includes: detecting whether the driver is unresponsive based on the image information collected by the camera and the driver's control information on the vehicle.
  • a second reminder when it is detected that the driver is unresponsive, a second reminder is issued, including: after detecting that the driver has not responded since the first reminder When the duration exceeds the first preset threshold, a second reminder is issued.
  • the first preset threshold is determined based on the driver's historical driving habits and/or image information collected by the camera; and when no response from the driver is detected
  • a third reminder is issued, including: when it is detected that the driver has not responded since the second reminder has been issued for a period exceeding the second preset threshold, a third reminder is sent, and the second preset threshold is It is determined based on the image information collected by the camera and/or the predicted fatigue of the driver.
  • the threshold of the response time of each reminder is dynamically adjusted, wherein the first preset threshold is determined based on the driver's historical driving habits and/or the image information collected by the camera, and the second preset threshold is determined based on The image information collected by the camera and/or the predicted fatigue of the driver is determined. For example, when it is predicted that the driver will be fatigued, the second preset threshold is set shorter, so that the next reminder can be issued sooner, which is beneficial to improve driving safety.
  • the image information collected by the camera includes one or more of the following: facial images, whether to drink water, and whether to answer or make calls; the driver's control of the vehicle
  • the information includes one or more of the following: whether to twist the steering wheel, whether to step on the brake, whether to step on the accelerator, and whether to turn the steering wheel lever.
  • the method further includes: exiting the automatic driving mode when the driver does not respond to multiple reminders.
  • the first parameter set further includes one or more of the following: the driver's blood pressure, body temperature and pulse; and the method further includes: When at least one of the blood pressure, body temperature and pulse meets the second preset condition, a first message is sent, and the first message is used to instruct the vehicle to send a distress signal and/or stop driving.
  • a first message is sent to instruct the vehicle to send a distress signal and/or stop driving. For example, when the body temperature of the driver exceeds its corresponding preset value, a first message is sent, so that the vehicle sends a distress signal, thereby ensuring the safety of the driver.
  • the present application provides an intelligent driving system, which includes: a parameter collection device for collecting a first parameter set, the first parameter set includes one or more of the following: respiratory rate, blood oxygen saturation and heart rate; the intelligent driving device is used to obtain the first parameter set from the parameter acquisition device, and based on the first parameter set, predict whether the driver is fatigued; and when the driver is predicted to be fatigued, send a reminder to Reminds the driver to pay attention to the driving situation of the vehicle.
  • the parameter collection device can be used to obtain one or more parameters of the driver to provide to the intelligent driving device, so that the intelligent driving device can predict whether the driver is based on one or more of the above parameters.
  • Fatigue that is, to determine whether the driver will be fatigued next, and to send a reminder to the driver if he will be fatigued.
  • the intelligent driving device predicts whether the driver will be fatigued through the above parameters, and then sends a reminder to the driver before the driver is tired, so that the driver can take over the vehicle in a short period of time, reducing the risk of safety accidents and improving safety. driver's safety.
  • the intelligent driving device is specifically configured to predict that the driver will be fatigued when the first parameter set satisfies the first preset condition.
  • the intelligent driving device can judge that the driver will be fatigued when the first parameter set satisfies the first preset condition, and a specific implementation method for predicting whether the driver is fatigued according to the first parameter set is given. In the case that the driver is predicted to be fatigued, the driver is reminded in advance, which is beneficial to improve the safety of the driver.
  • a possible design is that the first parameter set includes respiratory frequency, and the first preset condition includes that the respiratory frequency is less than a first preset value. Another possible design is that the first parameter set includes blood oxygen saturation, and the first preset condition includes that blood oxygen saturation is less than a second preset value. Another possible design is that the first parameter set includes heart rate, and the first preset condition includes that the heart rate is less than a third preset value.
  • each parameter in the first parameter set corresponds to a preset value, and when one or more parameters in the first parameter set are less than the corresponding preset value, it can be determined that the driver will be fatigued, In order to remind the driver in advance, it is beneficial to reduce the risk of safety accidents and improve the safety of the driver.
  • the intelligent driving device is specifically configured to issue reminders multiple times when the driver is predicted to be fatigued.
  • the intelligent driving device may send reminders to the driver multiple times in the case of predicting that the driver is fatigued, so as to remind the driver to pay attention to the driving situation of the vehicle. It can be understood that sending a reminder to the driver once may cause the driver not to respond, and sending reminders multiple times will help increase the possibility of the driver receiving the reminder and improve the safety of the driver.
  • the types of reminders include one or more of the following: visual reminders, auditory reminders, and tactile reminders.
  • multiple dimensions and types of reminders are provided, which improves the flexibility of the reminder issued by the intelligent driving device, and facilitates the driver to receive the reminder from the vehicle in time. For example, if the driver's eyes are not looking ahead, the visual reminder may not be effective. You can choose auditory reminder or tactile reminder, or even choose auditory reminder and tactile reminder to ensure that the driver can receive the reminder from the vehicle.
  • the intelligent driving device is specifically used to: issue a first reminder when the driver is predicted to be fatigued, and the type of the first reminder includes visual reminders, One of the auditory reminder and the tactile reminder; in the case that the driver is detected to be unresponsive, a second reminder is issued, and the type of the second reminder includes two types of visual reminder, auditory reminder and tactile reminder; When the driver does not respond, a third reminder is issued, and the types of the third reminder include visual reminders, auditory reminders and tactile reminders.
  • the first parameter set also includes the driver's historical driving habits and/or image information collected by the camera; and the intelligent driving device is also used for driving based on the history Habitual and/or graphic information to determine the type of first reminder.
  • the intelligent driving device can further combine the driver's historical driving habits and/or image information collected by the camera to determine the type of the first reminder. For example, the driver is currently in a state of not paying attention to the vehicle, the driver's historical driving habits indicate that the driver's ability to take over the vehicle is weak, and the driver is predicted to be fatigued through the first parameter, then the intensity of the first reminder can be Stronger, like visual and audible alerts for the first time.
  • the type of reminder can be more reasonably determined, which is beneficial for the driver to receive the reminder in a more timely manner and provides safety.
  • the intelligent driving device is further configured to detect whether the driver is unresponsive based on the image information collected by the camera and the driver's control information on the vehicle.
  • the intelligent driving device can determine whether the driver responds to the reminder based on the driver's control information and image information on the vehicle, which is beneficial to determine whether the reminder is valid, so that when the driver does not respond to the reminder If there is no response, it will continue to remind the driver, thereby ensuring that the driver pays attention to the driving situation of the vehicle, and then takes over the vehicle in time under special circumstances, reducing the risk of safety accidents.
  • the intelligent driving device is specifically configured to: detect that the driver has not responded for a period of time exceeding the first preset threshold after sending the first reminder , the second reminder is issued, the first preset threshold is determined based on the driver’s historical driving habits and/or image information collected by the camera; and when it is detected that the driver has not responded for more than In the case of the second preset threshold, a third reminder is issued, and the second preset threshold is determined based on the image information collected by the camera and/or the predicted fatigue of the driver.
  • the intelligent driving device can dynamically adjust the threshold of the response time for each reminder, wherein the first preset threshold is determined based on the driver's historical driving habits and/or image information collected by the camera, and the second preset threshold The threshold is determined based on the image information collected by the camera and/or the predicted fatigue of the driver. For example, when the intelligent driving device predicts that the driver will be fatigued, the second preset threshold is set shorter, so that the next reminder can be issued sooner, which is beneficial to improve driving safety.
  • the image information collected by the camera includes one or more of the following: facial images, whether to drink water, and whether to answer or make calls; the driver's control of the vehicle
  • the information includes one or more of the following: whether to twist the steering wheel, whether to step on the brake, whether to step on the accelerator, and whether to turn the steering wheel lever.
  • the intelligent driving device is further configured to exit the automatic driving mode when the driver does not respond to multiple reminders.
  • the first parameter set also includes one or more of the following: the driver's blood pressure, body temperature and pulse; When at least one of the blood pressure, body temperature and pulse meets the second preset condition, a first message is sent, and the first message instructs the vehicle to send a distress signal and/or stop driving.
  • the smart driving device when at least one of the driver's blood pressure, body temperature and pulse meets the second preset condition, the smart driving device sends a first message to instruct the vehicle to send a distress signal and/or stop driving. For example, when the body temperature of the driver exceeds its corresponding preset value, the intelligent driving device sends a first message, so that the vehicle sends a distress signal, thereby ensuring the safety of the driver.
  • the parameter collection device includes one or more of the following: a wearable device for collecting one or more of the following parameters: respiratory rate, blood oxygen saturation Degree, heart rate and pulse; smart seat, used to collect heart rate; camera, used to collect image information and/or body temperature.
  • the present application provides an intelligent driving device, including a unit for implementing the first aspect and the method in any possible implementation manner of the first aspect. It should be understood that each unit can realize corresponding functions by executing computer programs.
  • the present application provides an intelligent driving device, including a processor configured to execute the intelligent driving method described in the first aspect and any possible implementation manner of the first aspect.
  • the apparatus may also include memory for storing instructions and data.
  • the memory is coupled to the processor, and when the processor executes the instructions stored in the memory, the method described in the first aspect and any possible implementation manner of the first aspect may be implemented.
  • the device may further include a communication interface, which is used for the device to communicate with other devices.
  • the communication interface may be a transceiver, a circuit, a bus, a module or other types of communication interfaces.
  • the present application provides a system-on-a-chip, which includes at least one processor, configured to support the implementation of the functions involved in the above-mentioned first aspect and any possible implementation of the first aspect, such as receiving or processing Data and/or information involved in the methods described above.
  • the chip system further includes a memory, the memory is used to store program instructions and data, and the memory is located inside or outside the processor.
  • the system-on-a-chip may consist of chips, or may include chips and other discrete devices.
  • the present application provides a computer-readable storage medium, including a computer program, which, when run on a computer, causes the computer to implement the method in the first aspect and any possible implementation manner of the first aspect.
  • the present application provides a computer program product, the computer program product including: a computer program (also referred to as code, or an instruction), when the computer program is executed, the computer executes the first aspect and the And the method in any possible implementation manner of the first aspect.
  • a computer program also referred to as code, or an instruction
  • Figure 1 is a schematic diagram of a scene applicable to the method provided by the embodiment of the present application.
  • Fig. 2 is a schematic diagram of the system structure of the intelligent driving system provided by the embodiment of the present application.
  • FIG. 3 is a schematic flow diagram of an intelligent driving method provided in an embodiment of the present application.
  • FIG. 4 is a schematic flow diagram of a reminder issued by an intelligent driving device provided in an embodiment of the present application.
  • Fig. 5 is a schematic diagram of the driver's ability to take over when a reminder is issued according to an embodiment of the present application
  • Fig. 6 is a schematic block diagram of an intelligent driving device provided by an embodiment of the present application.
  • Fig. 7 is another schematic block diagram of the intelligent driving device provided by the embodiment of the present application.
  • words such as “first” and “second” are used to distinguish the same or similar items with basically the same function and effect.
  • the first preset condition and the second preset condition are for distinguishing different preset conditions, and the sequence thereof is not limited.
  • words such as “first” and “second” do not limit the quantity and execution order, and words such as “first” and “second” do not necessarily limit the difference.
  • “at least one item (items)” refers to one item (items) or multiple items (items).
  • “And/or” describes the association relationship of associated objects, indicating that there may be three types of relationships, for example, A and/or B, which can mean: A exists alone, A and B exist at the same time, and B exists alone, where A, B can be singular or plural.
  • the character “/” generally indicates that the contextual objects are an “or” relationship, but it does not exclude the situation that the contextual objects are an "and” relationship, and the specific meaning can be understood in conjunction with the context.
  • a, b, or c may mean: a, b, c; a and b; a and c; b and c; or a and b and c. Where a, b, c can be single or multiple.
  • the terms “comprising” and “having” and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or process that includes a series of steps or units
  • the apparatus is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to the process, method, product or apparatus.
  • the classification of intelligent driving is widely adopted by the classification standard given by the standard SAE J3016 of the International Society of Automotive Engineers (SAE).
  • SAE International Society of Automotive Engineers
  • automatic driving technology is divided into six levels from low to high, L0 to L5.
  • L0 has the lowest automation level, and L5 represents fully automatic driving (that is, no driver intervention is required under all conditions).
  • the driver is the only driver of the vehicle and needs to control all controls such as the steering wheel, accelerator and brake. But it can have active safety features such as automatic emergency braking (AEB).
  • AEB automatic emergency braking
  • the driver is still the sole driver of the vehicle and needs to control all controls such as the steering wheel, accelerator and brakes. But there can be more auxiliary/supportive functions, such as adaptive cruise control or lane keeping functions.
  • the vehicle's automatic driving system can drive the vehicle in certain situations, such as when traffic jams, the vehicle can use the traffic jam assist (traffic jam chauffeur) function to drive automatically, at this time the driver does not need to drive the vehicle; when needed At this time, the driver must take over the vehicle.
  • traffic jam assist traffic jam chauffeur
  • the regional driverless taxi (driverless taxi) is a typical L4 level autonomous driving scenario.
  • the L5 level represents fully automatic driving under any conditions and is the ultimate ideal level of autonomous driving. At present, only some vehicles can realize L2 autonomous driving technology, and it is still being improved.
  • the intelligent driving method described below can be applied to autonomous driving vehicles of L2 level and below, and also can be applied to future autonomous driving vehicles of L3 level and above, which is not limited in this embodiment of the present application. It should also be understood that in future L3 level and above self-driving vehicles, the vehicle can realize most of the driving functions, and when it is found that the driver is about to be in a state of fatigue, a reminder can be sent to the driver, so that the driver can take over the vehicle. In this embodiment of the present application, the driver taking over the vehicle means that the driver manually drives the vehicle without the assistance of the vehicle.
  • FIG. 1 is a schematic diagram of a scene applicable to a method in an embodiment of the present application.
  • the vehicle driven by the driver includes a smart seat 120 , and the smart seat 120 can be used to collect the driver's heart rate.
  • the driver can also wear a smart bracelet 110, which can be used to collect the driver's respiratory rate, blood oxygen saturation, heart rate and pulse.
  • both the smart bracelet 110 and the smart seat 120 may be referred to as parameter collection devices.
  • the parameter collection device can be used to collect the physiological parameters of the driver.
  • the parameter acquisition device is connected to an intelligent driving device (not shown in the figure), and the intelligent driving device can be deployed inside the vehicle, for example, it can be a domain controller, or other devices with the same or similar functions.
  • the parameter collection device can send the collected parameters to the intelligent driving device, so that the intelligent driving device can predict whether the driver is fatigued.
  • the parameter acquisition device shown in FIG. 1 is only an example, and should not constitute any limitation to this embodiment of the application.
  • the parameter collection device may also include a camera, and other types of wearable devices, such as smart watches.
  • the information collected by the parameter collection device is not limited to the respiratory rate, blood oxygen saturation, and heart rate listed above, but may also include images, body temperature, and the like. This application includes but is not limited to this.
  • the state of the driver is very important. As mentioned above, in the automatic driving technology of L2 level and below, the driver is still in a dominant position over the vehicle. During the driving process, the driver needs to pay attention to the vehicle in real time. If the driver is in a state of fatigue, safety accidents are likely to occur. In the automatic driving process of L3 level and above, the driver’s operation is less. At this time, the driver’s fatigue refers to the fatigue caused by the driver’s less activity and long-term monotonous response, which can also be called passive fatigue.
  • DMS driver monitoring system
  • DMS can obtain the image information of the driver through the camera, and determine the state of the driver according to the image information, for example, whether the driver's eyes are Looking ahead, whether the driver is yawning, etc.
  • emergencies may be encountered, such as road construction ahead, pedestrians suddenly appearing in front, etc. Therefore, the driver needs to pay attention to the vehicle and the surrounding environment in real time during the driving process of the vehicle.
  • the driver may have inattention, fatigue, etc., resulting in the inability to respond in time when encountering an emergency. Therefore, it is necessary to detect the driver's state in real time to remind the driver to pay attention to the driving situation of the vehicle, thereby improving safety. .
  • the above-mentioned DMS reminds the driver to operate the vehicle when the driver is fatigued through the camera. At this time, it is very likely that the driver cannot respond, which will lead to a higher risk of a safety accident for the driver and lower safety. Even in the process of automatic driving at L3 level and above, the driver may be required to take over the vehicle under special circumstances. If the driver is already in a state of fatigue, the driver may not have the ability to take over the vehicle.
  • this application provides an intelligent driving method, by detecting physiological parameters such as the driver's respiratory rate, blood oxygen saturation and heart rate, to predict whether the driver will be fatigued in the future, and when the driver will be fatigued
  • a reminder is sent to the driver to remind the driver to pay attention to the surrounding driving conditions, so that the driver is in a state of concentration, so that he can take over the vehicle in special circumstances, so as to improve driving safety.
  • the intelligent driving method provided by this application can also be applied to manual driving.
  • fatigue can be understood as the driver's frequent operation of the vehicle. Fatigue can also be called active fatigue.
  • the detection of the driver mentioned in the embodiment of the present application is carried out with the consent of the driver.
  • the detection of the driver in the embodiment of the present application does not involve Driver's privacy without violating their legal rights.
  • Fig. 2 is a schematic diagram of the system structure of the intelligent driving system provided by the embodiment of the present application.
  • An intelligent driving system 200 applicable to the method provided by the embodiment of the present application will be described in detail below with reference to FIG. 2 .
  • the intelligent driving system 200 includes a parameter acquisition device 210 (a wearable device 211 , a smart seat 212 and a camera 213 as shown in the figure) and an intelligent driving device 220 .
  • the parameter collection device 210 may be used to collect a first parameter set, and the first parameter set includes one or more of the following: respiratory rate, blood oxygen saturation and heart rate.
  • the wearable device 211 is used to collect one or more of the following parameters: respiratory rate, blood oxygen saturation, heart rate, pulse; the smart seat 212 is used to collect heart rate; the camera 213 is used to collect image information and/or body temperature.
  • the intelligent driving device 220 can be used to obtain the first parameter set from the parameter acquisition device 210, and based on the first parameter set, predict whether the driver is fatigued, and issue a reminder when the driver is predicted to be fatigued, to prompt The driver pays attention to the driving situation of the vehicle.
  • the intelligent driving device 220 is specifically configured to predict that the driver will be fatigued when the first parameter set satisfies the first preset condition.
  • the first parameter set includes respiratory rate, and the above-mentioned first preset condition includes that the respiratory rate is less than the first preset value; or the first parameter set includes blood oxygen saturation, and the above-mentioned first preset condition includes blood oxygen saturation less than the second preset value; or the first parameter set includes heart rate, and the above-mentioned first preset condition includes that the heart rate is less than the third preset value.
  • the intelligent driving device 220 is specifically configured to issue reminders multiple times when the driver is predicted to be fatigued.
  • the types of the above reminders include one or more of the following: visual reminders, auditory reminders and tactile reminders.
  • the intelligent driving device 220 is specifically used to: issue a first reminder when the driver is predicted to be fatigued, the type of the first reminder includes one of visual reminders, auditory reminders and tactile reminders; When the driver is unresponsive, a second reminder is issued, the type of the second reminder includes two types of visual reminder, auditory reminder and tactile reminder; when no response is detected from the driver, a third reminder is sent The type of the third reminder includes visual reminder, auditory reminder and tactile reminder.
  • the first parameter set further includes the driver's historical driving habits and/or image information collected by the camera; and the intelligent driving device 220 is further configured to determine the type of the first reminder based on the historical driving habits and/or image information.
  • the intelligent driving device 220 is also used to detect whether the driver is unresponsive based on the image information collected by the camera and the driver's control information on the vehicle.
  • the intelligent driving device 220 is specifically configured to: issue a second reminder when it is detected that the driver has not responded for a period of time exceeding the first preset threshold after sending the first reminder, and the above-mentioned first preset threshold is based on Determined by the driver's historical driving habits and/or image information collected by the camera; and when it is detected that the driver has not responded for more than the second preset threshold since the second reminder, a third reminder is issued , the above-mentioned second preset threshold is determined based on the image information collected by the camera and/or the predicted fatigue of the driver.
  • the image information collected by the camera includes one or more of the following: facial image, whether to drink water, and whether to answer or answer the phone; the driver’s control information on the vehicle includes one or more of the following: whether to twist the steering wheel, Whether to step on the brake, whether to step on the accelerator and whether to move the steering wheel lever.
  • the intelligent driving device 220 is also used to exit the automatic driving mode when the driver does not respond to multiple reminders.
  • the first parameter set also includes one or more of the following: the driver's blood pressure, body temperature and pulse; In the case of two preset conditions, a first message is sent, and the first message instructs the vehicle to send a distress signal and/or stop driving.
  • the structure shown in the embodiment of the present application does not constitute any limitation on the intelligent driving system 200.
  • the intelligent driving system 200 may also include more or less components than those shown in the illustration, or combine Some parts, or some parts split, or different part arrangements.
  • the illustrated components can be realized in hardware, software or a combination of software and hardware.
  • parameter acquisition device may also include sensors, such as gravity sensors, temperature sensors, and the like.
  • Fig. 3 is a schematic flowchart of an intelligent driving method 300 provided by an embodiment of the present application.
  • the method 300 shown in Fig. 3 may include steps 310 to 330, and each step in the method 300 will be described in detail below.
  • step 310 the intelligent driving device acquires a first parameter set.
  • the first parameter set includes one or more of the following: respiratory rate, blood oxygen saturation and heart rate.
  • Statistics have found that when the respiratory rate is lower than 16 beats/min, the driver is prone to drowsiness, and when the heart rate is lower than 60 beats/min, the driver is prone to drowsiness.
  • Pulse-respiration quotient refers to the ratio of heart rate to respiratory rate. It is an important indicator of the cardiopulmonary system, and it is also an important indicator of human physiology and pathophysiology research. When PRQ is lower than 4, the driver Get sleepy easily.
  • the above parameters can be used to determine whether the driver will be fatigued, which can be collectively referred to as physiological parameters herein, and the above physiological parameters can be used to detect the driver.
  • the intelligent driving device can obtain one or more of the above parameters to predict whether the driver will be fatigued.
  • the first parameter set may also include other physiological parameters that can be used to determine whether the driver will be fatigued, the present application includes but is not limited thereto.
  • the parameter collection device can be used to collect the first parameter set, wherein the parameter collection device includes one or more of the following: a wearable device for collecting one or more of the following parameters: respiratory rate, blood oxygen Saturation, heart rate and pulse; smart seat for collecting heart rate; camera for collecting image information and/or body temperature.
  • a wearable device for collecting one or more of the following parameters: respiratory rate, blood oxygen Saturation, heart rate and pulse
  • smart seat for collecting heart rate
  • camera for collecting image information and/or body temperature.
  • the intelligent driving device can obtain the first parameter set through communication with the above-mentioned parameter collection device.
  • the intelligent driving device can control the area network bus (control area network, CAN) signal through wireless fidelity (Wireless Fidelity, Wi-Fi), or turn Bluetooth to CAN signal, or directly realize the connection with the parameter acquisition device through CAN signal communication to acquire the first parameter set from the parameter acquisition device.
  • area network bus control area network, CAN
  • wireless fidelity Wireless Fidelity, Wi-Fi
  • Wi-Fi Wireless Fidelity
  • wearable devices can also be called wearable smart devices, which is a general term for the application of wearable technology to intelligently design daily wear and develop wearable devices, such as smart watches and bracelets.
  • a wearable device is a portable device that can be worn directly on the body or integrated into the user's clothing or accessories.
  • Wearable devices are not only a hardware device, but also achieve powerful functions through software support, data interaction, and cloud interaction.
  • Generalized wearable smart devices include full-featured, large-sized, complete or partial functions without relying on smart phones, such as smart watches or smart glasses, etc., and only focus on a certain type of application functions, and need to cooperate with other devices such as smart phones Use, such as various smart bracelets and smart jewelry for physical sign monitoring.
  • step 320 the intelligent driving device predicts whether the driver is fatigued based on the above-mentioned first parameter set.
  • the pre-judgment refers to that the state of the driver determined by the intelligent driving device based on the above-mentioned first parameter set is an imminent state.
  • the intelligent driving device predicts whether the driver is fatigued based on the respiratory rate, which means that the intelligent driving device determines whether the driver will be in a fatigued state based on the driver's respiratory rate at the current moment.
  • the intelligent driving device predicts that the driver will be fatigued when the first parameter set satisfies the first preset condition.
  • the first preset condition includes one or more preset conditions.
  • the first parameter set includes one or more parameters, and each parameter may correspond to a preset condition. After the intelligent driving device obtains the first parameter set, it judges whether the first parameter set satisfies the first preset condition, and if at least one parameter satisfies its corresponding preset condition, it is predicted that the driver will be fatigued; if the first parameter set If one or more of the parameters do not meet the corresponding preset conditions, it is predicted that the driver will not be fatigued.
  • the first parameter set includes respiratory frequency
  • the first preset condition includes that the respiratory frequency is less than a first preset value.
  • the breathing frequency corresponds to the first preset value. After the intelligent driving device obtains the breathing frequency, it judges whether the breathing frequency is less than the first preset value. If so, it predicts that the driver will be fatigued; fatigue.
  • the first parameter set includes blood oxygen saturation
  • the first preset condition includes that blood oxygen saturation is less than a second preset value.
  • the blood oxygen saturation corresponds to the second preset value.
  • the smart driving device After the smart driving device obtains the blood oxygen saturation, it judges whether the blood oxygen saturation is less than the second preset value. If yes, it predicts that the driver will be fatigued; if not, then Anticipate driver fatigue.
  • the first parameter set includes heart rate
  • the first preset condition includes that the heart rate is less than a third preset value.
  • the heart rate corresponds to the third preset value. After the intelligent driving device obtains the heart rate, it judges whether the heart rate is lower than the third preset value. If so, it predicts that the driver will be fatigued;
  • the above-mentioned multiple designs may be used alone or in combination, which is not limited in the present application.
  • the intelligent driving device predicts that the driver will be fatigued; if multiple parameters do not meet the above preset conditions, the intelligent driving device predicts Judge the driver will not be fatigued.
  • the first parameter set includes heart rate and respiratory rate
  • the intelligent driving device predicts that the driver will be fatigued.
  • the parameters included in the first parameter set and the corresponding preset conditions may not be limited to those listed herein, and the present application makes no limitation thereto.
  • the intelligent driving device can also predict whether the driver will be fatigued through other physiological parameters related to the driver's fatigue, which is not limited in this embodiment of the present application.
  • step 330 when the intelligent driving device predicts that the driver will be fatigued, a reminder is sent to remind the driver to pay attention to the driving situation of the vehicle.
  • the intelligent driving device When the intelligent driving device predicts that the driver will be fatigued, it will issue a reminder to remind the driver to pay attention to the driving situation of the vehicle, which allows the driver to have sufficient time to adjust the state, concentrate, and enter the focus of the vehicle.
  • the driver in the automatic driving technology of L3 level and above, the driver can also receive a reminder in advance, so that he can take over the vehicle in time in an emergency.
  • the type of reminder includes one or more of the following: visual reminder, auditory reminder and tactile reminder.
  • Visual reminder refers to reminding the driver by popping up relevant prompt information on the screen.
  • Auditory reminder refers to reminding the driver through voice broadcast.
  • Tactile reminder refers to reminding the driver by means of seat belt tightening, seat vibration, etc. That is to say, the intelligent driving device can send reminders from various dimensions of vision, hearing and touch, reminding the driver to the greatest extent so that he can pay attention to the vehicle in time.
  • a possible implementation is that, when the intelligent driving device predicts that the driver will be fatigued, one of the above-mentioned reminders is issued to the driver, or two types of the above-mentioned reminders are issued to the driver. reminders, or send three types of reminders to the driver in the above-mentioned reminder types.
  • sending a reminder includes: when the driver is predicted to be fatigued, sending reminders multiple times.
  • the intelligent driving device sends reminders to the driver multiple times, which is beneficial to avoid the situation that one reminder is invalid, thereby ensuring that the driver can effectively receive the reminders from the intelligent driving device.
  • a possible implementation is to issue a first reminder when the driver is predicted to be fatigued.
  • the type of first reminder includes one of visual reminder, auditory reminder and tactile reminder;
  • a second reminder is issued, and the type of the second reminder includes two types of visual reminder, auditory reminder and tactile reminder;
  • Types of reminders include visual reminders, auditory reminders, and tactile reminders.
  • the intelligent driving device sends out a visual reminder when it predicts that the driver will be fatigued; In the event of a situation, visual alerts, auditory alerts, and tactile alerts are issued.
  • the invalid reminder mentioned above may mean that the intelligent driving system issued a reminder but was not received by the driver, or that the driver received it but did not respond, such as not responding to the reminder and paying attention to the vehicle. Therefore, whether the reminder is invalid can be judged according to whether the driver responds after the reminder is sent.
  • the intelligent driving device can judge whether the driver responds after sending out the reminder according to the driver's manipulation information of the vehicle and the driver's image information collected by the camera.
  • the driver's control information on the vehicle includes one or more of the following: whether to twist the steering wheel, whether to step on the brake, whether to step on the accelerator, and whether to move the steering wheel lever.
  • the driver's control information on the vehicle may also include whether to step on the clutch, whether to honk the horn, and so on.
  • the above components may send messages to the intelligent driving device to instruct the driver to control the vehicle.
  • the intelligent driving device receives messages from the above-mentioned components of the vehicle, so as to obtain the driver's control information on the vehicle.
  • the image information collected by the camera refers to the driver's facial image and driver's actions captured by the camera, for example, whether the driver drinks water, whether he answers the phone, or whether he uses a mobile phone to type, etc.
  • the parameter collection device is also used to collect image information and information on the driver's manipulation of the vehicle to determine whether the driver responds. For example, after the intelligent driving device reminds for the first time, the image information of the driver is obtained in real time. According to the image information, it is determined that the driver's eyes are watching the front, and the driver makes a corresponding operation of shaking the steering wheel, then it is determined that the driver has responded. After the driving device sends out a reminder, the driver is in a state of paying attention to the vehicle. As mentioned above, the smart driving device can send multiple reminders. Wherein, the type of the first reminder may be determined based on historical driving habits and/or image information. The manner in which the smart driving device determines the type of the first reminder will be described in detail below.
  • the intelligent driving device determines the type of the first reminder based on historical driving habits. If the historical driving habits indicate that the driver has a strong ability to take over, the type of the first reminder can be any of the following: visual reminder, auditory reminder and tactile reminder. If the historical driving habits indicate that the driver's ability to take over is weak, the type of the first reminder can be any of the following two types: visual reminder, auditory reminder and tactile reminder.
  • the smart driving device determines the type of the first reminder based on the image information.
  • the intelligent driving device can acquire the characteristics of the driver based on the image, for example, the state of the driver's eyes, whether the driver answers the phone, and so on. For example, if it is determined from the image information that the driver's eyes are closed, or the driver's eyes are not looking ahead, therefore, even if a visual reminder is issued, the driver may not be able to notice, then the type of the first reminder can be an auditory reminder and/or or haptic reminders.
  • the type of the first reminder can be a visual reminder and/or a tactile reminder. For the sake of brevity, they are not listed here.
  • the intelligent driving device determines the type of the first reminder based on historical driving habits and image information.
  • the intelligent driving device can determine whether to select one reminder type or multiple reminder types for the first reminder according to the historical driving habits, and then determine the reminder type according to the image information. For example, if the historical driving habits indicate that the driver has a strong ability to take over, the smart driving device may determine to select a reminder type for the first time. Further, the intelligent driving device determines the type of reminder specifically selected in combination with the image information of the driver. For example, if the driver's eyes are not looking ahead, the type of reminder can be selected as auditory reminder or tactile reminder.
  • the intelligent driving device needs to obtain the driver's historical driving habits and the image information collected by the camera to determine the type of the first reminder. How to obtain the above parameters will be described in detail below.
  • the driver's historical driving habits include the strength of the driver's historical takeover ability.
  • the driver's historical driving data can indicate how long it took the driver to take over the vehicle in the past when an emergency occurred. If the time to complete the takeover is shorter, it indicates that the driver has a stronger takeover ability.
  • the smart driving device can obtain the driver's historical driving habits from the user data center, and the user data center can be deployed on the server.
  • the smart driving device can communicate with the server to obtain the driver's historical driving habits. Habit.
  • the image information collected by the camera refers to the driver's facial image and driver's actions captured by the camera, for example, whether the driver drinks water, whether he answers the phone, or whether he uses a mobile phone to type, etc.
  • the intelligent driving device can obtain image information from the parameter acquisition device.
  • the parameter collection device includes a camera, which can be used to collect image information of the driver and send the image information of the driver to the intelligent driving device.
  • the intelligent driving device acquires the image information of the driver.
  • the intelligent driving device After the intelligent driving device receives the image information from the camera, it processes the received image. For example, the intelligent driving device can perform digital processing, noise reduction, filtering or reconstruction on the image. It can be understood that for the specific steps of the above processing manner, reference may be made to known technologies, and for the sake of brevity, the image processing flow will not be described in detail here.
  • the intelligent driving device can further input the processed image into the trained neural network model to extract the characteristics of the driver.
  • the neural network model can be, for example, any of the following: convolutional neural networks (CNN), recurrent neural network (RNN), artificial neural network (ANN), residual neural network ( residual neural network, ResNet), etc.
  • CNN convolutional neural networks
  • RNN recurrent neural network
  • ANN artificial neural network
  • ResNet residual neural network
  • the intelligent driving device can train the above-mentioned neural network model based on a large number of images of drivers. For example, a large number of facial images of drivers and eye parts in the facial images can be input to the neural network model to train the neural network model to obtain a trained neural network model. Then the intelligent driving device inputs the captured image of the current driver into the trained neural network model to obtain the characteristics of the driver's eyes, such as whether the eyes are looking forward or not.
  • the intelligent driving device inputs the processed image into the trained neural network model, and can obtain the driver's eye state, such as blink frequency, whether the eyes are looking at the front of the windshield, whether the eyes are open, etc.
  • the intelligent driving device can also acquire the state of the driver's mouth based on the above neural network model, such as whether to yawn or not.
  • the intelligent driving device may also obtain whether the driver answers the phone, whether the driver drinks water, etc. based on the above-mentioned neural network model.
  • the driver can also identify the driver based on the above neural network model to confirm the identity of the driver, so as to confirm and verify the identity of the driver.
  • the intelligent driving device may further set a threshold for the driver's response time after each reminder, so as to issue the next reminder when the driver does not respond.
  • the intelligent driving device can determine the threshold of the response time for each reminder based on the driver's image information, historical driving habits, or predicted driver fatigue. In other words, the intelligent driving device can dynamically adjust the response time for each reminder. threshold. For example, if the intelligent driving device predicts that the driver will be fatigued, the threshold can be set shorter.
  • the smart driving device can send out multiple reminders.
  • the following takes sending three reminders as an example, and describes in detail the process of the intelligent driving device sending multiple reminders in combination with the above-mentioned threshold of each response time.
  • the intelligent driving device may issue a second reminder when it detects that the driver has not responded since the first reminder has been issued for a period exceeding a first preset threshold, and the first preset threshold is based on the driver's historical driving habits and/or
  • the image information collected by the camera is determined; when it is detected that the driver has not responded for more than the second preset threshold since the second reminder, the third reminder is issued, and the second preset threshold is based on the camera. It is determined based on the received image information and/or the predicted fatigue of the driver.
  • the first preset threshold is determined based on the driver's historical driving habits and/or image information collected by the camera.
  • the smart driving device may determine the first preset threshold based on the acquired historical driving habits.
  • the smart driving device pre-stores the correspondence between the level of takeover capability and the first preset threshold, such as the level of takeover capability is divided into 1 Up to 10 levels, each level corresponds to a value of the first preset threshold.
  • the first preset threshold can be set higher, and if the takeover capability is poor, the first preset threshold can be set lower.
  • the intelligent driving device may determine the first preset threshold based on the acquired image information. For example, the intelligent driving device pre-stores the corresponding relationship between the driver's eye state and the first preset threshold, such as the eyes looking forward corresponds to a The value of the first preset threshold.
  • the intelligent driving device can also determine the first preset threshold in combination with one or more of the following: vehicle driving information, road condition information, and automatic driving state determination.
  • vehicle driving information refers to the current driving speed, acceleration, etc. of the vehicle
  • automatic driving state refers to whether the automatic driving function is turned on. If it is turned on, the vehicle is in the automatic driving state; if it is not turned on, the vehicle is in the manual driving state.
  • the intelligent driving device determines the first preset threshold based on the driving information of the vehicle. For example, if the current vehicle is traveling at a faster speed, the first preset threshold may be set smaller, and if the current vehicle is traveling at a slower speed, the first preset threshold may be set higher.
  • the intelligent driving device determines the first preset threshold based on the driving information and road condition information of the vehicle. For example, the current vehicle is traveling at a slow speed and the road condition information shows that the road ahead is in good condition, such as no congestion, etc., the first preset threshold may be set larger. For the sake of brevity, they are not listed here.
  • FIG. 4 is a schematic flow diagram of a reminder issued by an intelligent driving device provided in an embodiment of the present application.
  • step 410 the intelligent driving device acquires a first parameter set.
  • step 420 the intelligent driving device determines whether to issue a reminder based on the first parameter set.
  • the intelligent driving device can predict whether the driver will be fatigued according to one or more of respiratory rate, blood oxygen saturation and heart rate, and based on the driver's historical driving habits and/or images collected by the camera The information determines a first preset threshold. For a specific method of determining the first preset threshold, reference may be made to the relevant description above. If the intelligent driving device predicts that the driver will be fatigued, it executes step 430, and if it predicts that the driver will not be fatigued, it returns to step 410.
  • step 430 the smart driving device sends out a visual reminder.
  • step 410 If the driver responds after sending out the visual reminder, the smart driving device returns to step 410; if the duration of no response after sending out the visual reminder exceeds the first preset threshold, the smart driving device executes step 440 to send out a visual reminder and an auditory reminder.
  • the first parameter set can be acquired in real time, and the second preset threshold can be determined according to the acquired image information and/or the predicted fatigue of the driver. If the driver responds after the visual and auditory reminders are issued, the intelligent driving device returns to step 410; Reminders, Audible Reminders and Haptic Reminders.
  • the first parameter set can be acquired in real time, and the third preset threshold can be determined according to the acquired image information and/or the predicted fatigue of the driver. If the duration of the driver's non-response exceeds the third preset threshold after the visual reminder, auditory reminder and tactile reminder are issued, the smart driving device executes step 460, sends a takeover request until the car is safely parked, and exits the automatic driving mode. If the driver responds, then return to step 410.
  • the smart driving device may perform more or fewer steps. For example, after the smart driving device executes step 420 and determines to issue a reminder, it may directly execute step 440 to issue a visual reminder and an auditory reminder, which is not limited in this embodiment of the present application.
  • the intelligent driving device may also obtain road condition information, such as road condition information from a navigation system, and determine the second preset threshold and/or the third preset threshold based on the road condition information. For example, the corresponding relationship between the road condition level and the value of the second preset threshold is stored in the intelligent driving device.
  • road condition information such as road condition information from a navigation system
  • determine the second preset threshold and/or the third preset threshold based on the road condition information For example, the corresponding relationship between the road condition level and the value of the second preset threshold is stored in the intelligent driving device.
  • road condition information such as road condition information from a navigation system
  • the intelligent driving device After the intelligent driving device sends out the above-mentioned multiple reminders, if the driver does not respond to the multiple reminders, exit the automatic driving mode.
  • the smart driving device requires the driver to take over the vehicle until it stops safely and exits the automatic driving mode. Furthermore, during this driving process, the intelligent driving device will prohibit the automatic driving function from being turned on again.
  • the intelligent driving device can also obtain parameters such as the driver's blood pressure and body temperature to determine the driver's physical state.
  • the first parameter set further includes one or more of the following: blood pressure, body temperature and pulse of the driver.
  • the above parameters can be used to determine whether the driver's physical condition is suitable for driving. For example, if the driver's blood pressure is too high, if the driver's temperature is too high, or if the driver's pulse is too fast. It can be understood that when the above parameters are too high, the driver's physical condition may be poor and unsuitable for driving.
  • a first message is sent, and the first message is used to instruct the vehicle to send a distress signal and/or stop driving.
  • Blood pressure, body temperature and pulse can respectively correspond to a preset value, for example, the second preset condition includes that the driver's blood pressure is higher than the fifth preset value; or the driver's body temperature is higher than the sixth preset value; or the driver's The pulse is higher than the seventh preset value.
  • the smart driving device sends a first message to the vehicle to prompt the vehicle to send a distress signal and/or stop driving.
  • Fig. 5 is a schematic diagram of the driver's ability to take over when a reminder is issued according to an embodiment of the present application.
  • the abscissa represents time
  • the ordinate represents the driver's ability to take over.
  • the specific takeover process of the driver can refer to known technologies, which will not be described here. It can be seen that at the moment when the reminder is issued after using the method provided by the embodiment of the present application, the driver's ability to take over is relatively high, indicating that the driver is more likely to successfully take over the vehicle in an emergency, thereby reducing the risk of safety accidents. risk and improve driving safety.
  • the intelligent driving device provided by the embodiment of the present application will be described in detail below with reference to FIG. 6 and FIG. 7 .
  • Fig. 6 is a schematic block diagram of an intelligent driving device 600 provided by an embodiment of the present application.
  • the apparatus 600 may include: a transceiver unit 610 and a processing unit 620 .
  • Each unit in the device 600 can be used to implement the corresponding process executed by the intelligent driving device in the embodiment shown in FIG. 3 or FIG. 4 .
  • the transceiver unit 610 can be used to obtain the first parameter set, and the first parameter set includes one or more of the following: respiratory rate, blood Oxygen saturation and heart rate; the processing unit 620 can be used to predict whether the driver is fatigued based on the first parameter set, and when the driver is predicted to be fatigued, send a reminder to remind the driver to pay attention to the driving situation of the vehicle .
  • the processing unit 620 can be used to predict whether the driver is fatigued based on the first parameter set, and when the driver is predicted to be fatigued, send a reminder to remind the driver to pay attention to the driving situation of the vehicle .
  • each functional unit in each embodiment of the present application may be integrated into one processor, or physically exist separately, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.
  • FIG. 7 is another schematic block diagram of an intelligent driving device 700 provided by an embodiment of the present application.
  • the device 700 may be a system on a chip, or may also be a device configured with a system on a chip to implement the driver detection function in the above method embodiment.
  • the system-on-a-chip may be composed of chips, or may include chips and other discrete components.
  • the apparatus 700 may include a processor 710 and a communication interface 720 .
  • the communication interface 720 can be used to communicate with other devices through a transmission medium, so that the devices used in the device 700 can communicate with other devices.
  • the communication interface 720 may be, for example, a transceiver, an interface, a bus, a circuit, or a device capable of implementing a transceiver function.
  • the processor 710 can use the communication interface 720 to input and output data, and implement the method described in the embodiment corresponding to FIG. 3 or FIG. 4 .
  • the device 700 can be used to implement the functions of the intelligent driving device in the above method embodiments.
  • the processor 710 may be used to control the communication interface 720 to obtain a first parameter set, the first parameter set includes one or more of the following Items: respiratory rate, blood oxygen saturation and heart rate; the processor 710 can also be used to predict whether the driver is fatigued based on the first parameter set, and to issue a reminder when the driver is predicted to be fatigued, to Reminds the driver to pay attention to the driving situation of the vehicle.
  • the processor 710 may be used to control the communication interface 720 to obtain a first parameter set, the first parameter set includes one or more of the following Items: respiratory rate, blood oxygen saturation and heart rate; the processor 710 can also be used to predict whether the driver is fatigued based on the first parameter set, and to issue a reminder when the driver is predicted to be fatigued, to Reminds the driver to pay attention to the driving situation of the vehicle.
  • the device 700 further includes at least one memory 730 for storing program instructions and/or data.
  • the memory 730 is coupled to the processor 710 .
  • the coupling in the embodiments of the present application is an indirect coupling or a communication connection between devices, units or modules, which may be in electrical, mechanical or other forms, and is used for information exchange between devices, units or modules.
  • Processor 710 may cooperate with memory 730 .
  • Processor 710 may execute program instructions stored in memory 730 . At least one of the at least one memory may be included in the processor.
  • the specific connection medium among the processor 710, the communication interface 720, and the memory 730 is not limited in the embodiment of the present application.
  • the processor 710 , the communication interface 720 and the memory 730 are connected through a bus 740 .
  • the bus 740 is represented by a thick line in FIG. 7 , and the connection manner between other components is only for schematic illustration and is not limited thereto.
  • the bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 7 , but it does not mean that there is only one bus or one type of bus.
  • the present application also provides a computer program product, and the computer program product includes: a computer program (also referred to as code, or an instruction), when the computer program is executed, the computer executes the implementation shown in FIG. 3 or FIG. 4 . method described in the example.
  • a computer program also referred to as code, or an instruction
  • the present application also provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program (also called a code, or an instruction).
  • a computer program also called a code, or an instruction.
  • the computer program When the computer program is executed, the computer is made to execute the method described in the embodiment shown in FIG. 3 or FIG. 4 .
  • the processor in the embodiment of the present application may be an integrated circuit chip that has a signal processing capability.
  • each step of the above-mentioned method embodiment can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software.
  • the above-mentioned processor can be a general-purpose processor, a digital signal processor (digital signal processor, DSP), an application specific integrated circuit (application specific integrated circuit, ASIC), a field programmable gate array (field programmable gate array, FPGA) or other possible Program logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • Program logic devices discrete gate or transistor logic devices, discrete hardware components.
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register.
  • the storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.
  • the memory in the embodiments of the present application may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories.
  • the non-volatile memory can be read-only memory (read-only memory, ROM), programmable read-only memory (programmable ROM, PROM), erasable programmable read-only memory (erasable PROM, EPROM), electrically programmable Erases programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • Volatile memory can be random access memory (RAM), which acts as external cache memory.
  • RAM random access memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • DRAM synchronous dynamic random access memory
  • SDRAM double data rate synchronous dynamic random access memory
  • ESDRAM enhanced synchronous dynamic random access memory
  • SLDRAM direct memory bus random access memory
  • direct rambus RAM direct rambus RAM
  • unit may be used to denote a computer-related entity, hardware, firmware, a combination of hardware and software, software, or software in execution.
  • the units described as discrete components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to realize the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • each functional unit may be fully or partially implemented by software, hardware, firmware or any combination thereof.
  • software When implemented using software, it may be implemented in whole or in part in the form of a computer program product.
  • the computer program product comprises one or more computer instructions (programs). When the computer program instructions (program) are loaded and executed on the computer, the processes or functions according to the embodiments of the present application will be generated in whole or in part.
  • the computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, server or data center Transmission to another website site, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.).
  • the computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media.
  • the available medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital versatile disc (digital video disc, DVD)), or a semiconductor medium (for example, a solid state disk (solid state disk, SSD) )wait.
  • a magnetic medium for example, a floppy disk, a hard disk, a magnetic tape
  • an optical medium for example, a digital versatile disc (digital video disc, DVD)
  • a semiconductor medium for example, a solid state disk (solid state disk, SSD)
  • the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: various media capable of storing program codes such as U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Mathematical Physics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

一种智能驾驶方法、系统和装置，该方法包括：获取第一参数集（310），该第一参数集包括如下一项或多项：呼吸频率、血氧饱和度和心率；基于第一参数集，预判驾驶员是否疲劳（320）；在预判到驾驶员将会疲劳的情况下，发出提醒，以提示驾驶员关注车辆的行驶情况（330）。通过获取驾驶员的呼吸频率、血氧饱和度或心率等生理参数，预判驾驶员未来是否会产生疲劳，并且在驾驶员将会疲劳的情况下，向驾驶员发出提醒，以使得驾驶员疲劳之前接到提醒，预先做好接管车辆的准备，以便于在特殊情况下有能力接管车辆，以利于提高行车的安全性。

Description

一种智能驾驶方法、系统和装置 技术领域
本申请涉及智能驾驶技术领域，尤其涉及一种智能驾驶方法、系统和装置。
背景技术
在车辆的驾驶过程中，驾驶员的状态至关重要。目前，国际自动机工程师协会将自动驾驶技术分为L0至L5六个等级，在L2等级及以下的自动驾驶技术中，驾驶员仍然处于对车辆的主导地位，需要驾驶员实时关注车辆以及周围的环境。在L3等级及以上自动驾驶技术中，自动驾驶系统对车辆处于主导地位，但驾驶员在特殊情况下可能需要接管车辆。可以看出，在车辆的行驶过程中，如果驾驶员的状态较差，如疲劳等，很有可能导致车辆发出提醒时，驾驶员无法回应，进而发生安全事故。
因此，希望提供一种智能驾驶方法，以降低发生安全事故的风险，进而提高安全性。
发明内容
本申请提供了一种智能驾驶方法、系统和装置，以期降低发生安全事故的风险，提高安全性。
第一方面，本申请提供了一种智能驾驶方法，该方法可以由智能驾驶装置执行，或者，也可以由配置在智能驾驶装置中的部件(如芯片、芯片系统等)执行，或者，还可以由能够实现全部或部分智能驾驶装置功能的逻辑模块或软件实现，本申请对此不作限定。
示例性地，该方法包括：获取第一参数集，该第一参数集包括如下一项或多项：呼吸频率、血氧饱和度和心率；基于上述第一参数集，预判驾驶员是否疲劳；在预判到驾驶员将会疲劳的情况下，发出提醒，以提示驾驶员关注车辆的行驶情况。
由于驾驶员的呼吸频率、血氧饱和度和心率等参数与驾驶员的疲劳状态有关，因此，本申请通过获取到的上述参数中的一项或多项，预判驾驶员是否会疲劳，即确定驾驶员接下来是否将会疲劳，在驾驶员将会疲劳的情况下，向其发出提醒。也就是在驾驶员疲劳之前，向其发出提醒，使得驾驶员关注车辆的驾驶情况，进而降低了发生安全事故的风险，提高了安全性。
结合第一方面，在第一方面的某些可能的实现方式中，基于第一参数集，预判驾驶员是否疲劳，包括：在第一参数集满足第一预设条件的情况下，预判驾驶员将会疲劳。
在上述方案中，第一参数集满足第一预设条件的情况下，判断驾驶员将会疲劳，给出了根据第一参数集预判驾驶员是否疲劳的具体实现方式，以便于预判出驾驶员将会疲劳的情况下，提前向驾驶员发出提醒，有利于提高驾驶员的安全性。
一种可能的设计是，第一参数集包括呼吸频率，第一预设条件包括：呼吸频率小于第一预设值。另一种可能的设计是，第一参数集包括血氧饱和度，第一预设条件包括：血氧饱和度小于第二预设值。又一种可能的设计是，第一参数集包括心率，第一预设条件包括： 心率小于第三预设值。在上述方案中，第一参数集中的每个参数可对应一个预设值，当第一参数集中的一个或多个参数小于其对应的预设值的情况下，即可以确定驾驶员将会疲劳，以便于提前对驾驶员做出提醒，有利于减少发生安全事故的风险，进而提高驾驶员的安全性。
应理解，上述多种设计可以单独使用，也可以结合使用，本申请对此不作限定。还应理解，第一参数集所包括的参数及其对应的预设条件可并不限于本文所列举，本申请对此不作限定。
结合第一方面，在第一方面的某些可能的实现方式中，在预判到驾驶员将会疲劳的情况下，发出提醒，包括：在预判到驾驶员将会疲劳的情况下，多次发出提醒。
在上述方案中，在预判到驾驶员疲劳的情况下，可以向其多次发出提醒，以提示驾驶员关注车辆的行驶情况。可以理解，向驾驶员发出一次提醒，可能会出现驾驶员并未响应的情况，多次发出提醒，有利于避免智能驾驶装置发出一次提醒无效的情况，进而有利于提高驾驶员接收到提醒的可能性，有利于提升驾驶员的安全性。
结合第一方面，在第一方面的某些可能的实现方式中，提醒的类型包括如下一项或多项：视觉提醒、听觉提醒和触觉提醒。
在上述方案中，智能驾驶装置可以选择任意一种或多种提醒类型进行提醒，通过提供了多个维度、多种类型的提醒，提高了提醒的灵活性，有利于驾驶员及时接收到车辆的提醒。例如，驾驶员的眼睛未注视前方，视觉提醒可能没有效果，可以选择听觉提醒或触觉提醒，甚至可以选择听觉提醒和触觉提醒，以保证驾驶员能够接收到车辆的提醒。
结合第一方面，在第一方面的某些可能的实现方式中，在预判到驾驶员将会疲劳的情况下，多次发出提醒，包括：在预判到驾驶员将会疲劳的情况下，发出首次提醒，首次提醒的类型包括视觉提醒、听觉提醒和触觉提醒中的一种；在检测到驾驶员无响应的情况下，发出第二次提醒，第二次提醒的类型包括视觉提醒、听觉提醒和触觉提醒中的两种；在检测到驾驶员无响应的情况下，发出第三次提醒，第三次提醒的类型包括视觉提醒、听觉提醒和触觉提醒。
在上述方案中，首次提醒的类型可以选择一种提醒类型，第二次提醒的类型可以选择任意两种，第三次提醒的类型可以选择三种，可以看出，提醒的类型增加，提醒的强度逐渐增强，提升了驾驶员接收到提醒的可能性，进而提高了驾驶员的安全性。
结合第一方面，在第一方面的某些可能的实现方式中，第一参数集还包括驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息；以及所述方法还包括：基于历史驾驶习惯和/或图像信息，确定首次提醒的类型。
在上述方案中，通过进一步地结合驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息，确定首次提醒的类型。示例性地，驾驶员当前处于不关注车辆的状态，驾驶员历史驾驶习惯指示该驾驶员接管车辆的能力较弱，且通过第一参数预判出驾驶员将会疲劳，则首次提醒的强度可以较强，如首次便发出视觉提醒和听觉提醒。通过结合驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息，能够更合理地确定提醒的类型，有利于驾驶员更及时地接收到提醒，提高了安全性。
结合第一方面，在第一方面的某些可能的实现方式中，所述方法还包括：基于摄像头采集到的图像信息和驾驶员对车辆的操控信息，检测驾驶员是否无响应。
在上述方案中，通过驾驶员对车辆的操控信息和图像信息确定出驾驶员是否对提醒做出相应的响应，有利于确定提醒是否有效，以便于在驾驶员对提醒并未做出响应的情况下，继续对驾驶员做出提醒，进而保证驾驶员关注车辆的行驶情况，进而可以在特殊情况下及时接管车辆，降低发生安全事故的风险。
结合第一方面，在第一方面的某些可能的实现方式中，在检测到驾驶员无响应的情况下，发出第二次提醒，包括：在检测到驾驶员自发出首次提醒之后无响应的时长超过第一预设门限的情况下，发出第二次提醒，第一预设门限是基于驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息确定的；以及在检测到驾驶员无响应的情况下，发出第三次提醒，包括：在检测到驾驶员自发出第二次提醒之后无响应的时长超过第二预设门限的情况下，发出第三次提醒，第二预设门限是基于摄像头采集到的图像信息和/或预判到的驾驶员是否疲劳确定的。
在上述方案中，动态调整每次提醒的响应时长的门限，其中，第一预设门限是基于驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息确定的，第二预设门限是基于摄像头采集到的图像信息和/或预判到的驾驶员是否疲劳确定的。例如，预判到驾驶员将会疲劳的情况下，将第二预设门限设置的较短，使得可以较快地发出下一次提醒，有利于提高驾驶的安全性。
结合第一方面，在第一方面的某些可能的实现方式中，摄像头采集到的图像信息包括如下一项或多项：面部图像、是否喝水和是否接打电话；驾驶员对车辆的操控信息包括如下一项或多项：是否扭动方向盘、是否踩踏刹车、是否踩踏油门和是否拨动方向盘拨杆。
结合第一方面，在第一方面的某些可能的实现方式中，所述方法还包括：在驾驶员对多次提醒均无响应的情况下，退出自动驾驶模式。
在上述方案中，在驾驶员对多次提醒均无响应的情况下，表明驾驶员并未关注车辆，无法及时接管车辆，容易发生安全事故，因此，由驾驶员接管车辆，直至安全停车，并退出自动驾驶模式，有利于降低发生安全事故的风险，提高安全性。
结合第一方面，在第一方面的某些可能的实现方式中，第一参数集还包括如下一项或多项：驾驶员的血压、体温和脉搏；以及所述方法还包括：在驾驶员的血压、体温和脉搏中的至少一项满足第二预设条件的情况下，发出第一消息，该第一消息用于指示车辆发出求救信号和/或停止行驶。
在上述方案中，在驾驶员的血压、体温和脉搏中的至少一项满足第二预设条件的情况下，发出第一消息，以指示车辆发出求救信号和/或停止行驶。例如，驾驶员的体温超过其对应的预设值的情况下，发出第一消息，以便于车辆发出求救信号，进而保证驾驶员的安全。
第二方面，本申请提供了一种智能驾驶系统，该系统包括：参数采集装置，用于采集第一参数集，上述第一参数集包括如下一项或多项：呼吸频率、血氧饱和度和心率；智能驾驶装置，用于从参数采集装置获取第一参数集，基于第一参数集，预判驾驶员是否疲劳；并在预判到驾驶员将会疲劳的情况下，发出提醒，以提示驾驶员关注车辆的行驶情况。
基于上述技术方案，参数采集装置可以用于获取驾驶员的一项或多项参数，以提供给智能驾驶装置，以便于智能驾驶装置基于上述参数中的一项或多项，预判驾驶员是否会疲劳，即确定驾驶员接下来是否将会处于疲劳，在驾驶员将会疲劳的情况下，向其发出提醒。 智能驾驶装置通过上述参数预判出驾驶员是否将会疲劳，进而在驾驶员疲劳之前，向其发出提醒，以便于驾驶员在较短的时间内接管车辆，降低了发生安全事故的风险，提高了驾驶员的安全性。
结合第二方面，在第二方面的某些可能的实现方式中，智能驾驶装置具体用于在第一参数集满足第一预设条件的情况下，预判驾驶员将会疲劳。
在上述方案中，智能驾驶装置可以在第一参数集满足第一预设条件的情况下，判断驾驶员将会疲劳，给出了根据第一参数集预判驾驶员是否疲劳的具体实现方式，在预判出驾驶员将会疲劳的情况下，提前向驾驶员发出提醒，有利于提高驾驶员的安全性。
一种可能的设计是，第一参数集包括呼吸频率，第一预设条件包括呼吸频率小于第一预设值。另一种可能的设计是，第一参数集包括血氧饱和度，第一预设条件包括血氧饱和度小于第二预设值。又一种可能的设计是，第一参数集包括心率，第一预设条件包括心率小于第三预设值。
在上述方案中，第一参数集中的每个参数对应一个预设值，当第一参数集中的一个或多个参数小于其对应的预设值的情况下，即可以确定驾驶员将会疲劳，以便于提前对驾驶员做出提醒，有利于减少发生安全事故的风险，进而提高驾驶员的安全性。
结合第二方面，在第二方面的某些可能的实现方式中，智能驾驶装置具体用于在预判到驾驶员将会疲劳的情况下，多次发出提醒。
在上述方案中，智能驾驶装置可以在预判到驾驶员疲劳的情况下，向其多次发出提醒，以提示驾驶员关注车辆的行驶情况。可以理解，向驾驶员发出一次提醒，可能会出现驾驶员并未响应的情况，多次发出提醒，有利于提高驾驶员接收到提醒的可能性，有利于提升驾驶员的安全性。
结合第二方面，在第二方面的某些可能的实现方式中，提醒的类型包括如下一项或多项：视觉提醒、听觉提醒和触觉提醒。
在上述方案中，提供了多个维度、多种提醒的类型，提高了智能驾驶装置发出提醒的灵活性，有利于驾驶员及时接收到车辆的提醒。例如，驾驶员的眼睛未注视前方，视觉提醒可能没有效果，可以选择听觉提醒或触觉提醒，甚至可以选择听觉提醒和触觉提醒，以保证驾驶员能够接收到车辆的提醒。
结合第二方面，在第二方面的某些可能的实现方式中，智能驾驶装置具体用于：在预判到驾驶员将会疲劳的情况下，发出首次提醒，首次提醒的类型包括视觉提醒、听觉提醒和触觉提醒中的一种；在检测到驾驶员无响应的情况下，发出第二次提醒，第二次提醒的类型包括视觉提醒、听觉提醒和触觉提醒中的两种；在检测到驾驶员无响应的情况下，发出第三次提醒，第三次提醒的类型包括视觉提醒、听觉提醒和触觉提醒。
在上述方案中，首次提醒的类型可以选择一种提醒类型，第二次提醒的类型可以选择任意两种，第三次提醒的类型可以选择三种，可以看出，提醒的类型增加，提醒的强度逐渐增强，提升了驾驶员接收到提醒的可能性，进而提高了驾驶员的安全性。
结合第二方面，在第二方面的某些可能的实现方式中，第一参数集还包括驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息；以及智能驾驶装置还用于基于历史驾驶习惯和/或图像信息，确定首次提醒的类型。
在上述方案中，智能驾驶装置可以进一步地结合驾驶员的历史驾驶习惯和/或摄像头采 集到的图像信息，确定首次提醒的类型。示例性地，驾驶员当前处于不关注车辆的状态，驾驶员历史驾驶习惯指示该驾驶员接管车辆的能力较弱，且通过第一参数预判出驾驶员将会疲劳，则首次提醒的强度可以较强，如首次便发出视觉提醒和听觉提醒。通过结合驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息，能够更合理地确定提醒的类型，有利于驾驶员更及时地接收到提醒，提供了安全性。
结合第二方面，在第二方面的某些可能的实现方式中，智能驾驶装置还用于基于摄像头采集的图像信息和驾驶员对车辆的操控信息，检测驾驶员是否无响应。
在上述方案中，智能驾驶装置可以基于驾驶员对车辆的操控信息和图像信息确定出驾驶员是否对提醒做出相应的响应，有利于确定提醒是否有效，以便于在驾驶员对提醒并未做出响应的情况下，继续对驾驶员做出提醒，进而保证驾驶员关注车辆的行驶情况，进而在特殊情况下及时接管车辆，降低发生安全事故的风险。
结合第二方面，在第二方面的某些可能的实现方式中，智能驾驶装置具体用于：在检测到驾驶员自发出所述首次提醒之后无响应的时长超过第一预设门限的情况下，发出第二次提醒，第一预设门限是基于驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息确定的；以及在检测到驾驶员自发出第二次提醒之后无响应的时长超过第二预设门限的情况下，发出第三次提醒，第二预设门限是基于摄像头采集到的图像信息和/或预判到的驾驶员是否疲劳确定的。
在上述方案中，智能驾驶装置可以动态调整每次提醒的响应时长的门限，其中，第一预设门限是基于驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息确定的，第二预设门限是基于摄像头采集到的图像信息和/或预判到的驾驶员是否疲劳确定的。例如，智能驾驶装置预判到驾驶员将会疲劳的情况下，将第二预设门限设置的较短，使得可以较快地发出下一次提醒，有利于提高驾驶的安全性。
结合第二方面，在第二方面的某些可能的实现方式中，摄像头采集到的图像信息包括如下一项或多项：面部图像、是否喝水和是否接打电话；驾驶员对车辆的操控信息包括如下一项或多项：是否扭动方向盘、是否踩踏刹车、是否踩踏油门和是否拨动方向盘拨杆。
结合第二方面，在第二方面的某些可能的实现方式中，智能驾驶装置还用于在驾驶员对多次提醒均无响应的情况下，退出自动驾驶模式。
在上述方案中，在驾驶员对多次提醒均无响应的情况下，表明驾驶员并未关注车辆，无法及时接管车辆，容易发生安全事故，因此，由驾驶员接管车辆，直至安全停车，并退出自动驾驶模式，有利于降低发生安全事故的风险，提高安全性。
结合第二方面，在第二方面的某些可能的实现方式中，第一参数集还包括如下一项或多项：驾驶员的血压、体温和脉搏；以及智能驾驶装置还用于在驾驶员的血压、体温和脉搏中的至少一项满足第二预设条件的情况下，发出第一消息，该第一消息指示车辆发出求救信号和/或停止行驶。
在上述方案中，在驾驶员的血压、体温和脉搏中的至少一项满足第二预设条件的情况下，智能驾驶装置发出第一消息，以指示车辆发出求救信号和/或停止行驶。例如，驾驶员的体温超过其对应的预设值的情况下，智能驾驶装置发出第一消息，以便于车辆发出求救信号，进而保证驾驶员的安全。
结合第二方面，在第二方面的某些可能的实现方式中，参数采集装置包括以下一项或 多项：可穿戴设备，用于采集以下一项或多项参数：呼吸频率、血氧饱和度、心率和脉搏；智能座椅，用于采集心率；摄像头，用于采集图像信息和/或体温。
第三方面，本申请提供了一种智能驾驶装置，包括用于实现第一方面以及第一方面任一种可能实现方式中的方法的单元。应理解，各个单元可通过执行计算机程序来实现相应的功能。
第四方面，本申请提供了一种智能驾驶装置，包括处理器，所述处理器用于执行第一方面以及第一方面任一种可能实现方式中所述的智能驾驶方法。
所述装置还可以包括存储器，用于存储指令和数据。所述存储器与所述处理器耦合，所述处理器执行所述存储器中存储的指令时，可以实现上述第一方面以及第一方面任一种可能实现方式中描述的方法。所述装置还可以包括通信接口，所述通信接口用于该装置与其它设备进行通信，示例性地，通信接口可以是收发器、电路、总线、模块或其它类型的通信接口。
第五方面，本申请提供了一种芯片系统，该芯片系统包括至少一个处理器，用于支持实现上述第一方面以及第一方面任一种可能实现方式中所涉及的功能，例如接收或处理上述方法中所涉及的数据和/或信息。
在一种可能的设计中，所述芯片系统还包括存储器，所述存储器用于保存程序指令和数据，存储器位于处理器之内或处理器之外。
该芯片系统可以由芯片构成，也可以包含芯片和其他分立器件。
第六方面，本申请提供了一种计算机可读存储介质，包括计算机程序，当其在计算机上运行时，使得计算机实现第一方面以及第一方面任一种可能实现方式中的方法。
第七方面，本申请提供了一种计算机程序产品，所述计算机程序产品包括：计算机程序(也可以称为代码，或指令)，当所述计算机程序被运行时，使得计算机执行第一方面以及以及第一方面任一种可能实现方式中的方法。
应当理解的是，本申请的第三方面至第七方面与本申请的第一方面的技术方案相对应，各方面及对应的可行实施方式所取得的有益效果相似，不再赘述。
附图说明
图1是适用于本申请实施例提供的方法的场景示意图；
图2是本申请实施例提供的智能驾驶系统的系统结构示意图；
图3是本申请实施例提供的智能驾驶方法的流程示意图；
图4是本申请实施例提供的智能驾驶装置发出提醒的流程示意图；
图5是本申请实施例提供的发出提醒时驾驶员的接管能力的示意图；
图6是本申请实施例提供的智能驾驶装置的示意性框图；
图7是本申请实施例提供的智能驾驶装置的另一示意性框图。
具体实施方式
下面将结合附图，对本申请中的技术方案进行描述。
为便于清楚描述本申请实施例的技术方案，首先做出如下说明。
第一，在本申请实施例中，采用了“第一”、“第二”等字样对功能和作用基本 相同的相同项或相似项进行区分。例如，第一预设条件和第二预设条件是为了区分不同的预设条件，并不对其先后顺序进行限定。本领域技术人员可以理解“第一”、“第二”等字样并不对数量和执行次序进行限定，并且“第一”、“第二”等字样也并不限定一定不同。
第二，在本申请实施例中，“至少一项(个)”是指一项(个)或者多项(个)。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B的情况，其中A，B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系，但并不排除表示前后关联对象是一种“和”的关系的情况，具体表示的含义可以结合上下文进行理解。“如下一项(个)或多项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如，a，b，或c中的一项或多项，可以表示：a，b，c；a和b；a和c；b和c；或a和b和c。其中a，b，c可以是单个，也可以是多个。
第三，在本申请实施例中，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
为便于理解本申请提供的方法，下面将对自动驾驶技术等级的划分进行详细描述。
目前，在智能驾驶领域，对智能驾驶的分级，所广泛采用的是由国际车辆工程师协会(society of automotive engineers，SAE)的标准SAE J3016所给出的分类标准。按照SAE的分级，将自动驾驶技术由低至高分为L0至L5共六个等级，L0的自动化等级最低，而L5则代表全自动驾驶(即在所有条件下均无需驾驶员介入)。SAE对于L0至L2等级的命名是“驾驶员支持功能(driver support features)”，对于L3至L5等级的命名是“自动驾驶功能(automated driving features)”。
对于L0等级，驾驶员是车辆的唯一驾驶者，需要控制方向盘，油门和制动等所有的控制装置。但可以拥有自动紧急刹车(autonomous emergency breaking，AEB)等主动安全功能。
对于L1等级和L2等级，驾驶员仍然是驾驶员是车辆的唯一驾驶者，需要控制方向盘，油门和制动等所有的控制装置。但是可以有更多的辅助性/支持性功能，例如自适应巡航或者车道保持等功能。
对于L3等级，车辆的自动驾驶系统可以在某些情况下驾驶车辆，例如当交通拥堵时，车辆可以使用交通拥堵辅助(traffic jam chauffeur)功能自动驾驶，此时驾驶员无需驾驶车辆；当需要的时候，驾驶员必须接管车辆。
对于L4等级，一般情况下不需要驾驶员接管，区域无人驾驶出租车(driverless taxi)是典型的L4级自动驾驶的场景。
L5等级代表任何条件下的全自动驾驶，是自动驾驶的终极理想水平。目前，只有部分车辆可以实现L2等级的自动驾驶技术，且仍在不断完善当中。
应理解，下文中所述的智能驾驶方法既可以适用于L2等级及以下的自动驾驶车辆，也可以适用于未来的L3等级及以上的自动驾驶车辆，本申请实施例对此不作限定。还 应理解，在未来的L3等级及以上的自动驾驶车辆中，车辆可以实现大部分驾驶功能，当发现驾驶员即将处于疲劳状态时，可以向驾驶员发出提醒，进而使得驾驶员接管车辆。在本申请实施例中，驾驶员接管车辆是指无需车辆辅助，驾驶员手动驾驶车辆。
图1是适用于本申请实施例的方法的场景示意图。如图1所示，驾驶员驾驶的车辆包括智能座椅120，智能座椅120可以用于采集驾驶员的心率。该驾驶员还可佩戴智能手环110，智能手环110可以用于采集驾驶员的呼吸频率、血氧饱和度、心率和脉搏等。在本申请实施例中，智能手环110和智能座椅120都可以称为参数采集装置。参数采集装置可用于采集驾驶员的生理参数。参数采集装置连接于智能驾驶装置(图中未示出)，智能驾驶装置可以部署在上述车辆的内部，例如可以是域控制器，或者其他具有相同或相似功能的设备。参数采集装置可以将采集到的参数发送给智能驾驶装置，以供智能驾驶装置预判驾驶员是否疲劳。
应理解，图1中所示的参数采集装置仅为示例，不应对本申请实施例构成任何限定。例如，参数采集装置还可以包括摄像头、以及其他类型的可穿戴设备，如智能手表等。参数采集装置采集的信息也并不仅限于上文所列举的呼吸频率、血氧饱和度、心率，还可以包括图像、体温等。本申请包含但不限于此。
在车辆的驾驶过程中，驾驶员的状态至关重要。前已述及，在L2等级及以下的自动驾驶技术中，驾驶员仍然处于对车辆的主导地位，在驾驶过程中需要驾驶员实时关注车辆，如果驾驶员处于疲劳状态，很可能发生安全事故。在L3等级及以上的自动驾驶过程中，驾驶员的操作较少，此时驾驶员的疲劳是指驾驶员的活动较少，长时间的单调反应所造成的疲劳，也可以称为被动疲劳。
目前，越来越多的车辆上安装有驾驶员监控系统(driver monitoring system，DMS)，DMS可以通过摄像头获取驾驶员的图像信息，根据图像信息确定驾驶员的状态，例如，驾驶员的眼睛是否注视前方、驾驶员是否打哈欠等。可以理解，在车辆驾驶过程中，可能会遇到突发事件，如前方道路施工、前方突然出现行人等，因此，驾驶员在车辆驾驶的过程中，需要实时关注车辆和周围环境。而驾驶员可能出现注意力不集中、疲劳等情况，导致在遇到紧急情况时无法及时做出反应，故需要实时检测驾驶员的状态，以提示驾驶员关注车辆的行驶情况，进而提高安全性。
上述DMS通过摄像头确定驾驶员疲劳的情况下，提醒驾驶员对车辆进行操作。此时，很可能驾驶员无法做出响应，进而导致驾驶员发生安全事故的风险较高，安全性较低。甚至在L3等级及以上的自动驾驶过程中，可能需要驾驶员在特殊情况下接管车辆，如果驾驶员已经处于疲劳状态，那驾驶员很可能没有接管车辆的能力。
为解决上述问题，本申请提供一种智能驾驶方法，通过检测驾驶员的呼吸频率、血氧饱和度和心率等生理参数，预判驾驶员未来是否将会产生疲劳，并且在驾驶员将会疲劳的情况下，向驾驶员发出提醒，以提示驾驶员注意周围行车情况，进而使得驾驶员处于注意力集中的状态，以便于在特殊情况下有能力接管车辆，以利于提高行车的安全性。
应理解，前已述及，本申请提供的智能驾驶方法也可以适用于手动驾驶，当本申请提供的智能驾驶方法应用于手动驾驶过程中时，疲劳可以理解为驾驶员频繁操作车辆所造成的疲劳，也可以称为主动疲劳。
还应理解，本申请实施例可以用于各种等级的自动驾驶技术，当实现L4等级或L5等级的自动驾驶时，驾驶员因无需操作车辆，也可以称为乘客。
下面以具体地实施例对本申请的技术方案以及本申请的技术方案如何解决上述技术问题进行详细说明。
需要说明的是，本申请实施例中所提及的对驾驶员的检测均是在征得驾驶员同意的情况下，对其进行检测，另外，本申请实施例中对驾驶员的检测不涉及驾驶员的隐私，且不侵犯其合法权利。
图2是本申请实施例提供的智能驾驶系统的系统结构示意图。下面将结合图2详细描述适用于本申请实施例提供的方法的智能驾驶系统200。
如图2所示，该智能驾驶系统200包括参数采集装置210(如图中所示的可穿戴设备211、智能座椅212和摄像头213)和智能驾驶装置220。参数采集装置210可以用于采集第一参数集，该第一参数集包括如下一项或多项：呼吸频率、血氧饱和度和心率。其中，可穿戴设备211用于采集以下一项或多项参数：呼吸频率、血氧饱和度、心率、脉搏；智能座椅212用于采集心率；摄像头213用于采集图像信息和/或体温。智能驾驶装置220可以用于从参数采集装置210获取第一参数集，基于第一参数集，预判驾驶员是否疲劳，并在预判到驾驶员将会疲劳的情况下，发出提醒，以提示驾驶员关注车辆的行驶情况。
可选地，智能驾驶装置220具体用于在第一参数集满足第一预设条件的情况下，预判驾驶员将会疲劳。
可选地，第一参数集包括呼吸频率，上述第一预设条件包括呼吸频率小于第一预设值；或第一参数集包括血氧饱和度，上述第一预设条件包括血氧饱和度小于第二预设值；或第一参数集包括心率，上述第一预设条件包括心率小于第三预设值。
可选地，智能驾驶装置220具体用于在预判到驾驶员将会疲劳的情况下，多次发出提醒。
可选地，上述提醒的类型包括如下一项或多项：视觉提醒、听觉提醒和触觉提醒。
可选地，智能驾驶装置220具体用于：在预判到驾驶员将会疲劳的情况下，发出首次提醒，该首次提醒的类型包括视觉提醒、听觉提醒和触觉提醒中的一种；在检测到驾驶员无响应的情况下，发出第二次提醒，该第二次提醒的类型包括视觉提醒、听觉提醒和触觉提醒中的两种；在检测到驾驶员无响应的情况下，发出第三次提醒，该第三次提醒的类型包括视觉提醒、听觉提醒和触觉提醒。
可选地，第一参数集还包括驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息；以及智能驾驶装置220还用于基于历史驾驶习惯和/或图像信息，确定首次提醒的类型。
可选地，智能驾驶装置220还用于基于摄像头采集的图像信息和驾驶员对车辆的操控信息，检测驾驶员是否无响应。
可选地，智能驾驶装置220具体用于：在检测到驾驶员自发出首次提醒之后无响应的时长超过第一预设门限的情况下，发出第二次提醒，上述第一预设门限是基于驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息确定的；以及在检测到驾驶员自发出第二次提醒之后无响应的时长超过第二预设门限的情况下，发出第三次提醒，上述第二预设门限是基于摄像头采集到的图像信息和/或预判到的驾驶员是否疲劳确定的。
可选地，摄像头采集到的图像信息包括如下一项或多项：面部图像、是否喝水和是否接打电话；驾驶员对车辆的操控信息包括如下一项或多项：是否扭动方向盘、是否踩踏刹车、是否踩踏油门和是否拨动方向盘拨杆。
可选地，智能驾驶装置220还用于在驾驶员对多次提醒均无响应的情况下，退出自动驾驶模式。
可选地，第一参数集还包括如下一项或多项：驾驶员的血压、体温和脉搏；以及智能驾驶装置220还用于在驾驶员的血压、体温和脉搏中的至少一项满足第二预设条件的情况下，发出第一消息，该第一消息指示车辆发出求救信号和/或停止行驶。
应理解，本申请实施例示意的结构并不构成对智能驾驶系统200的任何限定，在另一些实施例中，该智能驾驶系统200还可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。
应理解，上述参数采集装置还可以包括传感器，如重力传感器、温度传感器等。
图3是本申请实施例提供的智能驾驶方法300的流程示意图，图3所示的方法300可以包括步骤310至步骤330，下面将详细说明方法300中的各个步骤。
在步骤310中，智能驾驶装置获取第一参数集。
作为示例而非限定，第一参数集包括如下一项或多项：呼吸频率、血氧饱和度和心率。统计发现，呼吸频率低于16次/分钟时，驾驶员容易犯困，心率低于60次/分钟时，驾驶员容易犯困。脉搏呼吸熵(pulse-respiration quotient，PRQ)是指心率和呼吸频率的比值，是心肺系统的一个重要指标，更是人类生理学和病理生理学研究的一个重要指标，当PRQ低于4时，驾驶员容易犯困。因此，根据上述生理学和病理生理学的相关原理，上述参数均可以用以确定驾驶员是否将会疲劳，在本文中可统称为生理参数，上述生理参数可以用于对驾驶员的检测。智能驾驶装置可以获取上述参数中的一项或多项，以用于预判驾驶员是否将会疲劳。还应理解，除了上文所列举的生理参数之外，第一参数集还可以包括其他可用于确定驾驶员是否将会疲劳的生理参数，本申请包含但不限于此。
前已述及，参数采集装置可以用于采集第一参数集，其中，参数采集装置包括如下一项或多项：可穿戴设备，用于采集以下一项或多项参数：呼吸频率、血氧饱和度、心率和脉搏；智能座椅，用于采集心率；摄像头，用于采集图像信息和/或体温。
智能驾驶装置可以通过与上述参数采集装置的通信获取到第一参数集。
示例性地，智能驾驶装置可以通过无线保真(wireless fidelity，Wi-Fi)控制区域网络总线(control area network，CAN)信号，或者，蓝牙转CAN信号，或者直接通过CAN信号实现与参数采集装置的通信，以从参数采集装置中获取到第一参数集。
应理解，上述参数采集装置仅为示例，不应对本申请实施例构成任何限定。
需要说明的是，可穿戴设备也可以称为穿戴式智能设备，是应用穿戴式技术对日常穿戴进行智能化设计、开发出可以穿戴的设备的总称，如智能手表、手环等。可穿戴设备即可以直接穿在身上，或是整合到用户的衣服或配件的一种便携式设备。可穿戴设备不仅仅是一种硬件设备，更是通过软件支持以及数据交互、云端交互来实现强大的功能。广义穿戴式智能设备包括功能全、尺寸大、可不依赖智能手机实现完整或 者部分的功能，例如：智能手表或智能眼镜等，以及只专注于某一类应用功能，需要和其它设备如智能手机配合使用，如各类进行体征监测的智能手环、智能首饰等。
在步骤320中，智能驾驶装置基于上述第一参数集，预判驾驶员是否疲劳。
其中，预判是指智能驾驶装置基于上述第一参数集确定的驾驶员的状态是即将发生的状态。例如，智能驾驶装置基于呼吸频率预判驾驶员是否疲劳，是指智能驾驶装置基于当前时刻驾驶员的呼吸频率，确定驾驶员即将是否会处于疲劳状态。
一种可能的实现方式是，智能驾驶装置在第一参数集满足第一预设条件的情况下，预判驾驶员将会疲劳。第一预设条件包括一项或多项预设条件，由前可知，第一参数集包括一项或多项参数，每项参数可以对应一个预设条件。智能驾驶装置获取到第一参数集后，判断第一参数集是否满足第一预设条件，若至少一项参数满足其对应的预设条件，则预判驾驶员会疲劳；若第一参数集中的一项或多项参数均不满足其对应的预设条件，则预判驾驶员不会疲劳。
下面将详细描述第一参数集中的参数与其对应的预设条件。
一种可能的设计是，第一参数集包括呼吸频率，第一预设条件包括呼吸频率小于第一预设值。呼吸频率与第一预设值对应，智能驾驶装置获取到呼吸频率后，判断呼吸频率是否小于第一预设值，若是，则预判驾驶员会疲劳；若否，则预判驾驶员不会疲劳。
另一种可能的设计是，第一参数集包括血氧饱和度，第一预设条件包括血氧饱和度小于第二预设值。血氧饱和度与第二预设值对应，智能驾驶装置获取到血氧饱和度后，判断血氧饱和度是否小于第二预设值，若是，则预判驾驶员会疲劳；若否，则预判驾驶员不会疲劳。
又一种可能的设计是，第一参数集包括心率，第一预设条件包括心率小于第三预设值。心率与第三预设值对应，智能驾驶装置获取到心率后，判断心率是否小于第三预设值，若是，则预判驾驶员会疲劳；若否，则预判驾驶员不会疲劳。
应理解，上述多种设计可以单独使用，也可以结合使用，本申请对此不作限定。例如，当上述多种设计结合使用时，若至少一项参数满足上述预设条件，则智能驾驶装置预判驾驶员会疲劳；若多项参数均不满足上述预设条件，则智能驾驶装置预判驾驶员不会疲劳。又例如，当第一参数集中包括心率和呼吸频率时，若心率和呼吸频率的比值低于第四预设值，则智能驾驶装置预判驾驶员会疲劳。还应理解，第一参数集所包括的参数及其对应的预设条件可并不限于本文所列举，本申请对此不作限定。
还应理解，上文仅示出了呼吸频率、血氧饱和度和心率三种参数，但不应对本申请实施例构成任何限定。智能驾驶装置还可以通过其他与驾驶员疲劳相关的生理参数预判驾驶员是否会疲劳，本申请实施例对此不作限定。
在步骤330中，智能驾驶装置在预判到驾驶员将会疲劳的情况下，发出提醒，以提示驾驶员关注车辆的行驶情况。
智能驾驶装置在预判到驾驶员将会疲劳的情况下，发出提醒，以提示驾驶员关注车辆的行驶情况，这使得驾驶员可以有较充分的时间来调整状态、集中精力，进入关注车辆的状态，另外，在L3等级及以上的自动驾驶技术中，驾驶员也可以提前收到提醒，以便于可以在紧急情况下，有及时接管车辆的能力。
其中，提醒的类型包括如下一项或多项：视觉提醒、听觉提醒和触觉提醒。视觉提醒是指通过在屏幕上弹出相关的提示信息以提醒驾驶员。听觉提醒是指通过语音播报提醒驾驶员。触觉提醒是指通过安全带收紧、座椅震动等方式提醒驾驶员。也就是说，该智能驾驶装置可以从视觉、听觉和触觉各个维度来发出提醒，最大程度地提醒驾驶员，使其及时地关注车辆。
一种可能的实现方式是，智能驾驶装置在预判到驾驶员将会疲劳的情况下，向驾驶员发出上述提醒中的一种类型的提醒，或向驾驶员发出上述提醒类型中两种类型的提醒，或向驾驶员发出上述提醒类型中三种类型的提醒。
可选地，在预判到驾驶员将会疲劳的情况下，发出提醒，包括：在预判到驾驶员将会疲劳的情况下，多次发出提醒。
可以理解，智能驾驶装置向驾驶员多次发出提醒，有利于避免发出一次提醒无效的情况，进而保证驾驶员能够有效地接收到来自智能驾驶装置的提醒。
一种可能的实现方式是，在预判到驾驶员将会疲劳的情况下，发出首次提醒，首次提醒的类型包括视觉提醒、听觉提醒和触觉提醒中的一种；在检测到驾驶员无响应的情况下，发出第二次提醒，第二次提醒的类型包括视觉提醒、听觉提醒和触觉提醒中的两种；在检测到驾驶员无响应的情况下，发出第三次提醒，第三次提醒的类型包括视觉提醒、听觉提醒和触觉提醒。
示例性地，智能驾驶装置在预判到驾驶员将会疲劳的情况下，发出视觉提醒；在检测到驾驶员无响应的情况下，发出视觉提醒和听觉提醒；在检测到驾驶员再次无响应的情况下，发出视觉提醒、听觉提醒和触觉提醒。
可以看出，上述提醒的方式中，提醒的种类逐渐增多，提醒的强度逐渐增强。换言之，智能驾驶装置发出的提醒无效的情况下，便会加大对驾驶员的提醒强度。
应理解，上文所述的提醒无效可以是指智能驾驶系统发出提醒，但未被驾驶员接收到，或者，驾驶员接收到但无响应，比如未响应于该提醒，关注车辆。因此，提醒是否无效可依据发出提醒后驾驶员是否有响应来判断。
示例性地，智能驾驶装置可以通过驾驶员对车辆的操控信息和摄像头采集的驾驶员的图像信息判断发出提醒后驾驶员是否有响应。其中，驾驶员对车辆的操控信息包括如下一项或多项：是否扭动方向盘、是否踩踏刹车、是否踩踏油门和是否拨动方向盘拨杆。
应理解，上述操控信息仅为示例，不应对本申请实施例构成任何限定。例如，驾驶员对车辆的操控信息还可以包括是否踩踏离合、是否按喇叭等。
还应理解，驾驶员对车辆部件(如方向盘)做出相应的操作后，上述部件可以向智能驾驶装置发送消息，以指示驾驶员对车辆的操控。相应地，智能驾驶装置接收来自车辆的上述部件的消息，以获取到驾驶员对车辆的操控信息。
摄像头采集到的图像信息是指通过摄像头拍摄的驾驶员的面部图像、驾驶员的动作等，例如，驾驶员是否喝水、是否接打电话或是否使用手机打字等。
一种可能的实现方式是，参数采集装置还用于采集图像信息和驾驶员对车辆的操控信息，确定驾驶员是否做出响应。例如，智能驾驶装置首次提醒后，实时获取驾驶员的图像信息，根据图像信息确定驾驶员的眼睛注视前方，且驾驶员做出相应的晃动 方向盘的操作，则确定驾驶员有响应，换言之，智能驾驶装置发出提醒后，驾驶员对车辆处于关注状态。上文已提及，智能驾驶装置可以发出多次提醒。其中，首次提醒的类型可以基于历史驾驶习惯和/或图像信息确定。下面将对智能驾驶装置确定首次提醒的类型的方式进行详细描述。
一种可能的实现方式是，智能驾驶装置基于历史驾驶习惯确定首次提醒的类型。若历史驾驶习惯指示驾驶员的接管能力较强，则首次提醒的类型可以是如下任意一种：视觉提醒、听觉提醒和触觉提醒。若历史驾驶习惯指示驾驶员的接管能力较弱，则首次提醒的类型可以是如下任意两种：视觉提醒、听觉提醒和触觉提醒。
又一种可能的实现方式是，智能驾驶装置基于图像信息确定首次提醒的类型。前已述及，智能驾驶装置可以根据图像获取到驾驶员的特征，例如，驾驶员的眼睛状态、驾驶员是否接打电话等。一示例，若根据图像信息确定驾驶员的眼睛处于闭合状态、或驾驶员的眼睛未注视前方，因此，即使发出视觉提醒，驾驶员可能无法注意到，则首次提醒的类型可以选择听觉提醒和/或触觉提醒。又一示例，若根据图像信息确定驾驶员在戴着耳机听音乐，则首次提醒的类型可以选择视觉提醒和/或触觉提醒。为了简洁，此处不再一一列举。
再一种可能的实现方式是，智能驾驶装置基于历史驾驶习惯和图像信息确定首次提醒的类型。智能驾驶装置可以根据历史驾驶习惯确定首次提醒选择一种提醒类型还是多种提醒类型，进而根据图像信息确定提醒的类型。一示例，若历史驾驶习惯指示驾驶员的接管能力较强，则智能驾驶装置可以确定首次提醒选择一种提醒类型。进一步地，智能驾驶装置结合驾驶员的图像信息确定具体选择的提醒的类型。例如，驾驶员的眼睛未注视前方，则提醒的类型可以选择听觉提醒或触觉提醒。
由上可知，智能驾驶装置需要获取驾驶员的历史驾驶习惯和摄像头采集到的图像信息，以确定发出的首次提醒的类型。下面将详细描述如何获取上述参数。
驾驶员的历史驾驶习惯包括驾驶员历史的接管能力的强弱。例如，驾驶员的历史驾驶数据可以指示以往驾驶员在遇到突发事件时完成接管车辆的时间的长短，若完成接管的时间较短，表示驾驶员的接管能力较强。
一种可能的设计是，智能驾驶装置可以从用户数据中心获取驾驶员的历史驾驶习惯，用户数据中心可以部署在服务器上，换言之，智能驾驶装置可以和服务器进行通信，以获取驾驶员的历史驾驶习惯。
摄像头采集到的图像信息是指通过摄像头拍摄的驾驶员的面部图像、驾驶员的动作等，例如，驾驶员是否喝水、是否接打电话或是否使用手机打字等。智能驾驶装置可以从参数采集装置中获取图像信息。参数采集装置包括摄像头，摄像头可以用于采集驾驶员的图像信息，并将驾驶员的图像信息发送给智能驾驶装置。相应地，智能驾驶装置获取到驾驶员的图像信息。
智能驾驶装置接收到来自摄像头的图像信息后，对接收到的图像进行处理。例如，智能驾驶装置可以对图像进行数字化处理、降噪、滤波或重建等。可以理解，上述处理方式的具体步骤可以参看已知的技术，为了简洁，此处不再详述对图像的处理流程。
智能驾驶装置可以进一步地将处理后的图像输入至训练好的神经网络模型中，以提取驾驶员的特征。神经网络模型例如可以是如下任意一种：卷积神经网络 (convolutional neural networks，CNN)、递归神经网络(recurrent neural network，RNN)、人工神经网络(artificial neural network，ANN)、残差神经网络(residual neural network，ResNet)等。智能驾驶装置可以基于大量的驾驶员的图像训练上述神经网络模型。例如，可以将驾驶员大量的面部图像和面部图像中的眼睛部位输入至神经网络模型，以训练该神经网络模型，得到训练好的神经网络模型。则智能驾驶装置将拍摄到的当前驾驶员的图像输入至训练好的神经网络模型，即可得到驾驶员的眼睛部位的特征，如眼睛是否注视前方等。
一示例，智能驾驶装置将处理后的图像输入至训练好的神经网络模型中，可以获取到驾驶员的眼睛状态，如眨眼频率、眼睛是否注视挡风玻璃前方、眼睛是否睁开等。又一示例，智能驾驶装置基于上述神经网络模型还可以获取到驾驶员的嘴部状态，如是否打哈欠等。又一示例，智能驾驶装置基于上述神经网络模型还可以获取到驾驶员是否接打电话、是否喝水等。
需要说明的是，驾驶员基于上述神经网络模型还可以对驾驶员进行身份识别，确认该驾驶员的身份标识，以便于确认验证该驾驶员的身份。
应理解，智能驾驶装置可以进一步地设置每次提醒后驾驶员的响应时长的门限，以便于在驾驶员无响应的情况下，发出下一次提醒。
示例性地，智能驾驶装置可以基于驾驶员的图像信息、历史驾驶习惯或预判的驾驶员是否疲劳确定每次提醒的响应时长的门限，换言之，智能驾驶装置可以动态调整每次提醒的响应时长的门限。例如，智能驾驶装置预判到驾驶员将会疲劳，则可以将门限设置的更短一些。
前文已提及，智能驾驶装置可以发出多次提醒。下面以发出三次提醒为例，结合上述每次响应时长的门限，详细描述智能驾驶装置发出多次提醒的过程。
智能驾驶装置可以在检测到驾驶员自发出首次提醒之后无响应的时长超过第一预设门限的情况下，发出第二次提醒，第一预设门限是基于驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息确定的；在检测到驾驶员自发出第二次提醒之后无响应的时长超过第二预设门限的情况下，发出第三次提醒，第二预设门限是基于摄像头采集到的图像信息和/或预判到的驾驶员是否疲劳确定的。
其中，第一预设门限是基于驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息确定的。一示例，智能驾驶装置可以基于获取到的历史驾驶习惯确定第一预设门限，例如，智能驾驶装置中预存有接管能力等级和第一预设门限的对应关系，如接管能力等级分为1级至10级，每一级对应一个第一预设门限的取值。其中，接管能力较强，则第一预设门限可以设置的较高，若接管能力较差，则第一预设门限可以设置的较低。
又一示例，智能驾驶装置可以基于获取到的图像信息确定第一预设门限，例如，智能驾驶装置中预存有驾驶员的眼睛状态和第一预设门限的对应关系，如眼睛注视前方对应一个第一预设门限的取值。
可以理解，智能驾驶装置还可以结合如下一项或多项确定第一预设门限：车辆的行驶信息、路况信息、和自动驾驶状态确定。其中，当前车辆的行驶信息是指当前车辆的行驶速度、加速度等，自动驾驶状态是指是否开启自动驾驶功能，若开启，车辆处于自动驾驶状态，若未开启，车辆处于手动驾驶状态。
一示例，智能驾驶装置基于车辆的行驶信息确定第一预设门限。例如，当前车辆的行驶速度较快，可以将第一预设门限设置的较小，当前车辆的行驶速度较慢，可以将第一预设门限设置的较大。
又一示例，智能驾驶装置基于车辆的行驶信息和路况信息确定第一预设门限。例如，当前车辆的行驶速度较慢且路况信息显示前方道路状况较好，如无拥堵等，可以将第一预设门限设置的较大。为了简洁，此处不再一一列举。
图4是本申请实施例提供的智能驾驶装置发出提醒的流程示意图。
如图4所示，在步骤410中，智能驾驶装置获取第一参数集。
在步骤420中，智能驾驶装置基于第一参数集判断是否发出提醒。
示例性地，智能驾驶装置可以根据呼吸频率、血氧饱和度和心率中的一项或多项，预判驾驶员是否将会疲劳，并根据驾驶员的历史驾驶习惯和/或摄像头采集的图像信息确定第一预设门限。具体的确定第一预设门限的方法可参看上文的相关描述。智能驾驶装置在预判到驾驶员将会疲劳的情况下，执行步骤430，在预判到驾驶员不会疲劳的情况下，返回步骤410。
在步骤430中，智能驾驶装置发出视觉提醒。
若发出视觉提醒后驾驶员有响应，则智能驾驶装置返回步骤410；若发出视觉提醒后无响应的时长超过第一预设门限，则智能驾驶装置执行步骤440，发出视觉提醒和听觉提醒。
可以理解，智能驾驶装置发出视觉提醒后，可以实时获取第一参数集，根据获取到的图像信息和/或预判到的驾驶员是否疲劳确定第二预设门限。若发出视觉提醒和听觉提醒后驾驶员有响应，则智能驾驶装置返回步骤410；若发出视觉提醒和听觉提醒后无响应的时长超过第二预设门限，则智能驾驶装置执行步骤450，发出视觉提醒、听觉提醒和触觉提醒。
可以理解，智能驾驶装置发出视觉提醒和听觉提醒后，可以实时获取第一参数集，根据获取到的图像信息和/或预判到的驾驶员是否疲劳确定第三预设门限。若发出视觉提醒、听觉提醒和触觉提醒后驾驶员无响应的时长超过第三预设门限，则智能驾驶装置执行步骤460，发出接管请求直至安全停车，退出自动驾驶模式。若驾驶员有响应，则返回步骤410。
应理解，图4所示的步骤仅为示例，不应对本申请实施例构成任何限定。在另外的实施例中，智能驾驶装置可以执行更多或更少的步骤。例如，智能驾驶装置执行步骤420，确定发出提醒后，可以直接执行步骤440，发出视觉提醒和听觉提醒，本申请实施例对此不作限定。
还应理解，智能驾驶装置还可以获取路况信息，如从导航系统中路况信息，基于路况信息确定第二预设门限和/或第三预设门限。例如，智能驾驶装置中预存路况等级和第二预设门限的取值的对应关系。一种可能的设计是，路况越好，路况等级越高，路况等级越高，第二预设门限的越高。
智能驾驶装置发出上述多次提醒后，驾驶员对多次提醒均无响应的情况下，退出自动驾驶模式。
若驾驶员对多次提醒均无响应，则智能驾驶装置要求驾驶员接管车辆直至安全停 车，退出自动驾驶模式。进一步地，在此次行车过程中，智能驾驶装置将禁止再次开启自动驾驶功能。
应理解，在自动驾驶或手动驾驶的过程中，若驾驶员的身体状态较差，可能容易发生安全事故。因此，智能驾驶装置还可以获取驾驶员的血压、体温等参数，以确定驾驶员的身体状态。
示例性地，第一参数集还包括如下一项或多项：驾驶员的血压、体温和脉搏。
上述参数可以用于确定驾驶员的身体状态是否适合驾驶。例如，驾驶员的血压是否过高、驾驶员的体温是否偏高或驾驶员的脉搏是否过快。可以理解，当上述参数偏高的情况下，驾驶员的身体状态可能较差，不适合驾驶。
在驾驶员的血压、体温和脉搏中的至少一项满足第二预设条件的情况下，发出第一消息，第一消息用于指示车辆发出求救信号和/或停止行驶。
血压、体温和脉搏可以分别对应一个预设值，例如，第二预设条件包括驾驶员的血压高于第五预设值；或驾驶员的体温高于第六预设值；或驾驶员的脉搏高于第七预设值。示例性地，在驾驶员的血压高于第五预设值的情况下，智能驾驶装置向车辆发出第一消息，以提示车辆发出求救信号和/或停止行驶。
图5是本申请实施例提供的发出提醒时驾驶员的接管能力的示意图。如图5所示，横坐标代表时间，纵坐标代表驾驶员的接管能力。使用本申请实施例提供的方法后，智能驾驶装置发出提醒的时刻为t0，未使用本申请提供的方法时DMS发出的提醒时刻为t1，t0至t1是疲劳发生阶段，t2至t4是从接管请求发出至接管完成的接管时段。t2至t4，驾驶员具体的接管过程可以参考已知的技术，此处不再描述。可以看出，使用本申请实施例提供的方法后发出提醒的时刻，驾驶员的接管能力较高，说明驾驶员在遇到紧急情况时成功接管车辆的可能性较高，进而降低了发生安全事故的风险，提高了行车的安全性。
基于上述技术方案，通过检测驾驶员的呼吸频率、血氧饱和度或心率等生理参数，预判驾驶员未来是否会产生疲劳，并且在驾驶员将会疲劳的情况下，向驾驶员发出提醒，以提示驾驶员注意周围行车情况，在驾驶员疲劳之前向驾驶员发出提醒，进而使得驾驶员处于注意力集中的状态，以便于在特殊情况下有能力接管车辆，降低了发生安全事故的风险，提高了行车的安全性。
下文将结合图6和图7详细说明本申请实施例提供的智能驾驶装置。
图6是本申请实施例提供的智能驾驶装置600的示意性框图。如图6所示，该装置600可以包括：收发单元610和处理单元620。该装置600中的各单元可用于实现图3或图4所示的实施例中智能驾驶装置执行的相应流程。
当该装置600用于执行上述方法实施例中智能驾驶装置执行的步骤时，其中，收发单元610可用于获取第一参数集，该第一参数集包括如下一项或多项：呼吸频率、血氧饱和度和心率；处理单元620可用于基于第一参数集，预判驾驶员是否疲劳，并在预判到驾驶员将会疲劳的情况下，发出提醒，以提示驾驶员关注车辆的行驶情况。具体参见方法实施例中的详细描述，此处不作赘述。
应理解，各单元执行上述相应步骤的具体过程在上述方法实施例中已经详细说明，为了简洁，在此不再赘述。
还应理解，本申请实施例中对单元的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。另外，在本申请各个实施例中的各功能单元可以集成在一个处理器中，也可以是单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
图7是本申请实施例提供的智能驾驶装置700的另一示意性框图。该装置700可以为芯片系统，或者，也可以为配置了芯片系统，以用于实现上述方法实施例中驾驶员检测功能的装置。在本申请实施例中，芯片系统可以由芯片构成，也可以包含芯片和其他分立元器件。
如图7所示，该装置700可以包括处理器710和通信接口720。其中，通信接口720可用于通过传输介质和其它设备进行通信，从而用于装置700中的装置可以和其它设备进行通信。所述通信接口720例如可以是收发器、接口、总线、电路或者能够实现收发功能的装置。处理器710可利用通信接口720输入输出数据，并用于实现图3或图4对应的实施例中所述的方法。具体地，该装置700可用于实现上述方法实施例中智能驾驶装置的功能。
示例性地，若该装置700用于实现图3所示的实施例中所述的方法，该处理器710可用于控制通信接口720获取第一参数集，第一参数集包括如下一项或多项：呼吸频率、血氧饱和度和心率；该处理器710还可用于基于第一参数集，预判驾驶员是否疲劳，并在预判到驾驶员将会疲劳的情况下，发出提醒，以提示驾驶员关注车辆的行驶情况。具体参见方法实施例中的详细描述，此处不作赘述。
可选地，该装置700还包括至少一个存储器730，用于存储程序指令和/或数据。存储器730和处理器710耦合。本申请实施例中的耦合是装置、单元或模块之间的间接耦合或通信连接，可以是电性，机械或其它的形式，用于装置、单元或模块之间的信息交互。处理器710可能和存储器730协同操作。处理器710可能执行存储器730中存储的程序指令。所述至少一个存储器中的至少一个可以包括于处理器中。
本申请实施例中不限定上述处理器710、通信接口720以及存储器730之间的具体连接介质。本申请实施例在图7中以处理器710、通信接口720以及存储器730之间通过总线740连接。总线740在图7中以粗线表示，其它部件之间的连接方式，仅是进行示意性说明，并不引以为限。所述总线可以分为地址总线、数据总线、控制总线等。为便于表示，图7中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
本申请还提供一种计算机程序产品，所述计算机程序产品包括：计算机程序(也可以称为代码，或指令)，当所述计算机程序被运行时，使得计算机执行图3或图4所示实施例中所述的方法。
本申请还提供一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序(也可以称为代码，或指令)。当所述计算机程序被运行时，使得计算机执行图3或图4所示实施例中所述的方法。
应理解，本申请实施例中的处理器可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电 路或者软件形式的指令完成。上述的处理器可以是通用处理器、数字信号处理器(digital signal processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、分立门电路或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。
还应理解，本申请实施例中的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-only memory，ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic RAM，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。应注意，本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
本说明书中使用的术语“单元”、“模块”等，可用于表示计算机相关的实体、硬件、固件、硬件和软件的组合、软件、或执行中的软件。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各种说明性逻辑块(illustrative logical block)和步骤(step)，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。在本申请所提供的几个实施例中，应该理解到，所揭露的装置、设备和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分立部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例 方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
在上述实施例中，各功能单元的功能可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令(程序)。在计算机上加载和执行所述计算机程序指令(程序)时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，数字通用光盘(digital video disc，DVD))、或者半导体介质(例如固态硬盘(solid state disk，SSD))等。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (29)

  1. 一种智能驾驶方法，其特征在于，包括：
    获取第一参数集，所述第一参数集包括如下一项或多项：呼吸频率、血氧饱和度和心率；
    基于所述第一参数集，预判所述驾驶员是否疲劳；
    在预判到所述驾驶员将会疲劳的情况下，发出提醒，以提示驾驶员关注车辆的行驶情况。
  2. 如权利要求1所述的方法，其特征在于，所述基于所述第一参数集，预判所述驾驶员是否疲劳，包括：
    在所述第一参数集满足第一预设条件的情况下，预判所述驾驶员将会疲劳。
  3. 如权利要求2所述的方法，其特征在于，所述第一参数集包括呼吸频率，所述第一预设条件包括所述呼吸频率小于第一预设值；或
    所述第一参数集包括血氧饱和度，所述第一预设条件包括所述血氧饱和度小于第二预设值；或
    所述第一参数集包括心率，所述第一预设条件包括所述心率小于第三预设值。
  4. 如权利要求1至3中任一项所述的方法，其特征在于，所述在预判到所述驾驶员将会疲劳的情况下，发出提醒，包括：
    在预判到所述驾驶员将会疲劳的情况下，多次发出提醒。
  5. 如权利要求4所述的方法，其特征在于，所述提醒的类型包括如下一项或多项：视觉提醒、听觉提醒和触觉提醒。
  6. 如权利要求5所述的方法，其特征在于，所述在预判到所述驾驶员将会疲劳的情况下，多次发出提醒，包括：
    在预判到所述驾驶员将会疲劳的情况下，发出首次提醒，所述首次提醒的类型包括视觉提醒、听觉提醒和触觉提醒中的一种；
    在检测到所述驾驶员无响应的情况下，发出第二次提醒，所述第二次提醒的类型包括视觉提醒、听觉提醒和触觉提醒中的两种；
    在检测到所述驾驶员无响应的情况下，发出第三次提醒，所述第三次提醒的类型包括视觉提醒、听觉提醒和触觉提醒。
  7. 如权利要求6所述的方法，其特征在于，所述第一参数集还包括所述驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息；以及
    所述方法还包括：
    基于所述历史驾驶习惯和/或所述图像信息，确定首次提醒的类型。
  8. 如权利要求6或7所述的方法，其特征在于，所述方法还包括：
    基于摄像头采集到的图像信息和所述驾驶员对车辆的操控信息，检测所述驾驶员是否无响应。
  9. 如权利要求6至8中任一项所述的方法，其特征在于，所述在检测到所述驾驶员无响应的情况下，发出第二次提醒，包括：
    在检测到所述驾驶员自发出所述首次提醒之后无响应的时长超过第一预设门限的 情况下，发出所述第二次提醒，所述第一预设门限是基于所述驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息确定的；以及
    所述在检测到所述驾驶员无响应的情况下，发出第三次提醒，包括：
    在检测到所述驾驶员自发出所述第二次提醒之后无响应的时长超过第二预设门限的情况下，发出所述第三次提醒，所述第二预设门限是基于摄像头采集到的图像信息和/或预判到的所述驾驶员是否疲劳确定的。
  10. 如权利要求8所述的方法，其特征在于，所述摄像头采集到的图像信息包括如下一项或多项：面部图像、是否喝水和是否接打电话；
    所述驾驶员对车辆的操控信息包括如下一项或多项：是否扭动方向盘、是否踩踏刹车、是否踩踏油门和是否拨动方向盘拨杆。
  11. 如权利要求3至10中任一项所述的方法，其特征在于，所述方法还包括：
    在所述驾驶员对所述多次提醒均无响应的情况下，退出自动驾驶模式。
  12. 如权利要求11所述的方法，其特征在于，所述第一参数集还包括如下一项或多项：所述驾驶员的血压、体温和脉搏；以及
    所述方法还包括：
    在所述驾驶员的血压、体温和脉搏中的至少一项满足第二预设条件的情况下，发出第一消息，所述第一消息用于指示车辆发出求救信号和/或停止行驶。
  13. 一种智能驾驶系统，其特征在于，包括：
    参数采集装置，用于采集第一参数集，所述第一参数集包括如下一项或多项：呼吸频率、血氧饱和度和心率；
    智能驾驶装置，用于从所述参数采集装置获取所述第一参数集，基于所述第一参数集，预判所述驾驶员是否疲劳；并在预判到所述驾驶员将会疲劳的情况下，发出提醒，以提示驾驶员关注车辆的行驶情况。
  14. 如权利要求13所述的系统，其特征在于，所述智能驾驶装置具体用于在所述第一参数集满足第一预设条件的情况下，预判所述驾驶员将会疲劳。
  15. 如权利要求14所述的系统，其特征在于，所述第一参数集包括呼吸频率，所述第一预设条件包括所述呼吸频率小于第一预设值；或
    所述第一参数集包括血氧饱和度，所述第一预设条件包括所述血氧饱和度小于第二预设值；或
    所述第一参数集包括心率，所述第一预设条件包括所述心率小于第三预设值。
  16. 如权利要求13至15中任一项所述的系统，其特征在于，所述智能驾驶装置具体用于在预判到所述驾驶员将会疲劳的情况下，多次发出提醒。
  17. 如权利要求16所述的系统，其特征在于，所述提醒的类型包括如下一项或多项：视觉提醒、听觉提醒和触觉提醒。
  18. 如权利要求17所述的系统，其特征在于，所述智能驾驶装置具体用于：
    在预判到所述驾驶员将会疲劳的情况下，发出首次提醒，所述首次提醒的类型包括视觉提醒、听觉提醒和触觉提醒中的一种；
    在检测到所述驾驶员无响应的情况下，发出第二次提醒，所述第二次提醒的类型包括视觉提醒、听觉提醒和触觉提醒中的两种；
    在检测到所述驾驶员无响应的情况下，发出第三次提醒，所述第三次提醒的类型包括视觉提醒、听觉提醒和触觉提醒。
  19. 如权利要求18所述的系统，其特征在于，所述第一参数集还包括所述驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息；以及
    所述智能驾驶装置还用于基于所述历史驾驶习惯和/或所述图像信息，确定首次提醒的类型。
  20. 如权利要求18或19所述的系统，其特征在于，所述智能驾驶装置还用于基于摄像头采集的图像信息和所述驾驶员对车辆的操控信息，检测所述驾驶员是否无响应。
  21. 如权利要求18至20中任一项所述的系统，其特征在于，所述智能驾驶装置具体用于：
    在检测到所述驾驶员自发出所述首次提醒之后无响应的时长超过第一预设门限的情况下，发出所述第二次提醒，所述第一预设门限是基于所述驾驶员的历史驾驶习惯和/或摄像头采集到的图像信息确定的；以及
    在检测到所述驾驶员自发出所述第二次提醒之后无响应的时长超过第二预设门限的情况下，发出所述第三次提醒，所述第二预设门限是基于摄像头采集到的图像信息和/或预判到的所述驾驶员是否疲劳确定的。
  22. 如权利要求20所述的系统，其特征在于，所述摄像头采集到的图像信息包括如下一项或多项：面部图像、是否喝水和是否接打电话；
    所述驾驶员对车辆的操控信息包括如下一项或多项：是否扭动方向盘、是否踩踏刹车、是否踩踏油门和是否拨动方向盘拨杆。
  23. 如权利要求15至22中任一项所述的系统，其特征在于，所述智能驾驶装置还用于在所述驾驶员对所述多次提醒均无响应的情况下，退出自动驾驶模式。
  24. 如权利要求23所述的系统，其特征在于，所述第一参数集还包括如下一项或多项：所述驾驶员的血压、体温和脉搏；以及
    所述智能驾驶装置还用于在所述驾驶员的血压、体温和脉搏中的至少一项满足第二预设条件的情况下，发出第一消息，所述第一消息指示车辆发出求救信号和/或停止行驶。
  25. 如权利要求13至24中任一项所述的系统，其特征在于，所述参数采集装置包括以下一项或多项：
    可穿戴设备，用于采集以下一项或多项参数：呼吸频率、血氧饱和度、心率和脉搏；
    智能座椅，用于采集心率；
    摄像头，用于采集图像信息和/或体温。
  26. 一种智能驾驶装置，其特征在于，包括用于执行如权利要求1至12中任一项所述的方法的单元。
  27. 一种智能驾驶装置，其特征在于，包括存储器与处理器；其中，
    所述存储器用于存储程序代码；
    所述处理器用于调用所述程序代码以用于实现如权利要求1至12中任一项所述的 方法。
  28. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中储有计算机执行指令，所述计算机执行指令被处理器执行时用于实现如权利要求1至12任一项所述的方法。
  29. 一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现权利要求1至12中任一项所述的方法。
PCT/CN2021/141791 2021-12-27 2021-12-27 一种智能驾驶方法、系统和装置 WO2023122913A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/141791 WO2023122913A1 (zh) 2021-12-27 2021-12-27 一种智能驾驶方法、系统和装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/141791 WO2023122913A1 (zh) 2021-12-27 2021-12-27 一种智能驾驶方法、系统和装置

Publications (1)

Publication Number Publication Date
WO2023122913A1 true WO2023122913A1 (zh) 2023-07-06

Family

ID=86996845

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/141791 WO2023122913A1 (zh) 2021-12-27 2021-12-27 一种智能驾驶方法、系统和装置

Country Status (1)

Country Link
WO (1) WO2023122913A1 (zh)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130070043A1 (en) * 2011-09-19 2013-03-21 Nir Geva Vehicle driver monitor and a method for monitoring a driver
CN107252313A (zh) * 2017-05-25 2017-10-17 深圳市卡迪赛克科技有限公司 一种安全驾驶的监测方法及系统、汽车、可读存储介质
CN108464839A (zh) * 2018-03-22 2018-08-31 东华大学 一种基于机器学习的车载疲劳驾驶监测预警系统
JP2019021154A (ja) * 2017-07-20 2019-02-07 アルパイン株式会社 覚醒機能を備えた電子装置、覚醒プログラムおよび覚醒方法
CN109410524A (zh) * 2018-12-06 2019-03-01 四川大学锦城学院 一种驾驶员疲劳监测系统及其监测方法
US20190083022A1 (en) * 2017-09-15 2019-03-21 Hsin Ming Huang Fatigue driving monitoring device
CN112699793A (zh) * 2020-12-29 2021-04-23 长安大学 一种基于随机森林的疲劳驾驶检测优化识别方法
CN113284320A (zh) * 2021-04-01 2021-08-20 上海工程技术大学 一种列车司机疲劳状态的超前预测方法及系统

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130070043A1 (en) * 2011-09-19 2013-03-21 Nir Geva Vehicle driver monitor and a method for monitoring a driver
CN107252313A (zh) * 2017-05-25 2017-10-17 深圳市卡迪赛克科技有限公司 一种安全驾驶的监测方法及系统、汽车、可读存储介质
JP2019021154A (ja) * 2017-07-20 2019-02-07 アルパイン株式会社 覚醒機能を備えた電子装置、覚醒プログラムおよび覚醒方法
US20190083022A1 (en) * 2017-09-15 2019-03-21 Hsin Ming Huang Fatigue driving monitoring device
CN108464839A (zh) * 2018-03-22 2018-08-31 东华大学 一种基于机器学习的车载疲劳驾驶监测预警系统
CN109410524A (zh) * 2018-12-06 2019-03-01 四川大学锦城学院 一种驾驶员疲劳监测系统及其监测方法
CN112699793A (zh) * 2020-12-29 2021-04-23 长安大学 一种基于随机森林的疲劳驾驶检测优化识别方法
CN113284320A (zh) * 2021-04-01 2021-08-20 上海工程技术大学 一种列车司机疲劳状态的超前预测方法及系统

Similar Documents

Publication Publication Date Title
JP7080598B2 (ja) 車両制御装置および車両制御方法
WO2019095937A1 (zh) 一种碰撞预警方法及装置
JP7352566B2 (ja) 情報処理装置、移動装置、および方法、並びにプログラム
US10635101B2 (en) Methods and systems for preventing an autonomous vehicle from transitioning from an autonomous driving mode to a manual driving mode based on a risk model
US10150478B2 (en) System and method for providing a notification of an automated restart of vehicle movement
US20200216095A1 (en) Vehicle driving assistance apparatus
US10829130B2 (en) Automated driver assistance system
CN113345204A (zh) 一种车载远程疲劳唤醒方法及其唤醒系统
WO2018058266A1 (zh) 一种基于移动终端的提示方法及系统
JP2007528815A (ja) 運転者の行動解釈に基づいて自動車のサブシステムを制御する方法および機構
JP2004533732A (ja) 状況認識感知無線通信装置及び方法
US10752172B2 (en) System and method to control a vehicle interface for human perception optimization
WO2016103468A1 (ja) 衝突回避システム及び衝突回避方法
CN209795467U (zh) 一种疲劳驾驶检测系统和车辆
WO2018150677A1 (ja) 運転切替支援装置、及び運転切替支援方法
JP5712712B2 (ja) 車載機能制御装置
WO2018168121A1 (ja) 運転状態判定装置、運転状態判定方法及び運転状態判定のためのプログラム
WO2020054618A1 (ja) 車両用装置及び運転支援プログラム
JP2021096696A (ja) 車両用状態報知装置及び車両用状態報知方法
US10719724B2 (en) Safety system for an automobile
DE112019000475T5 (de) Überwachung der aufmerksamkeit von fahrzeuginsassen für autonome fahrzeuge
WO2023122913A1 (zh) 一种智能驾驶方法、系统和装置
WO2024046091A1 (zh) 一种驾驶员提醒方法、装置、系统和移动载体
JP6627810B2 (ja) 運転モード切替制御装置、方法およびプログラム
JP2020101869A (ja) 制御装置及びプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21969299

Country of ref document: EP

Kind code of ref document: A1