Driver state confirmation method and device based on automatic driving

Abstract

The invention provides a driver state confirmation method and device based on automatic driving, and relates to the technical field of automatic driving. When the method is executed, the driving condition of a vehicle is obtained in real time when the vehicle is in an automatic driving state, then the driving condition is input into a trigger rule model to obtain a comprehensive risk value, then when the comprehensive risk value exceeds a comprehensive risk threshold value, the types of risk factors which cause the comprehensive risk to exceed the comprehensive risk threshold value are obtained, and the types of the risk factors are determined according to the types of the risk factors. And then, calling a preset driver state inspection action library by utilizing the types of the risk factors to obtain a driver state inspection task, and finally, determining the driver state by executing the driver state inspection task. In this way, the driver state check task is determined through the category of the risk factor that causes the integrated risk to exceed the integrated risk threshold, and the driver state is determined by executing the driver state check task, so that the driver state can be accurately confirmed in automatic driving.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method and device for confirming a driver's status based on autonomous driving. Background Art

[0002] The autonomous driving system is responsible for controlling the vehicle. The driver does not need to pay attention to the road ahead for a long time and can perform other tasks during driving. However, when the system cannot handle a situation, the driver must control the vehicle within a limited time. During the process of taking over the driving rights, if the driver is not ready, it is very easy to cause a traffic accident due to human error. Therefore, during the process of autonomous driving, how to efficiently confirm the driver's status and evaluate the driver's ability to complete the driving task, so as to provide reference for the autonomous driving system and decide whether to transfer the driving rights, is one of the key technical issues for the safe operation of autonomous driving vehicles.

[0003] In the prior art, the driver's facial expression, eye focus and eye closure are obtained to confirm whether the driver is paying attention to the road ahead. However, since the driver does not need to pay attention to the road ahead for a long time in the state of automatic driving, the confirmation of the driver's state is not accurate.

[0004] In summary, how to accurately confirm the driver's status during autonomous driving is a problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] In view of this, the present application provides a driver status confirmation method and device based on automatic driving, aiming to accurately confirm the driver status during automatic driving.

[0006] In a first aspect, the present application provides a method for confirming a driver's state based on automatic driving, comprising:

[0007] When the vehicle is in an automatic driving state, obtaining the driving condition of the vehicle in real time;

[0008] Inputting the driving situation into the trigger rule model to obtain a comprehensive risk value;

[0009] When the comprehensive risk value exceeds the comprehensive risk threshold, obtaining the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold;

[0010] Using the type of risk factor, a preset driver status check action library is called to obtain a driver status check task;

[0011] By executing the driver status check task, the driver status is determined.

[0012] Optionally, determining the driver status by executing the driver status check task includes:

[0013] Execute the driver status check task;

[0014] Collecting the driver's response operation to the driver status check task to obtain a driver response parameter;

[0015] The driver response parameters are input into the driver status assessment model to obtain a comprehensive driver status score.

[0016] Optionally, before inputting the driving situation into the trigger rule model to obtain a comprehensive risk value, the method further includes:

[0017] Constructing the trigger rule model;

[0018] The formula of the trigger rule model is:

[0019] T=η a R env +η b R beh +η c R pos ;

[0020] T is the comprehensive risk value, R env is the external road environment risk factor, the R beh is the driver behavior risk factor, the R pos is the driver's sitting posture risk factor, the η a is the weight coefficient of the external road environment risk factor, and the η b is the weight coefficient of the driver behavior risk factor, and the η c is the weight coefficient of the driver's sitting posture risk factor.

[0021] Optionally, the step of inputting the driving situation into the trigger rule model to obtain a comprehensive risk value includes:

[0022] Inputting the driving situation into the trigger rule model; the driving situation includes positioning data, traffic environment information, navigation map prompt information, real-time driving behavior data and driver seat status information;

[0023] If the positioning data, the traffic environment information and the navigation map prompt information meet the external road environment risk factor setting condition, the external road environment risk factor is set to true to obtain the external road environment risk factor value;

[0024] If the real-time driving behavior data meets the driver behavior risk factor setting condition, the driver behavior risk factor is set to true to obtain the driver behavior risk factor value;

[0025] If the driver's seat state information satisfies the driver's sitting posture risk factor setting condition, the driver's sitting posture risk factor is set to true to obtain the driver's sitting posture risk factor value;

[0026] The comprehensive risk value is determined using the external road environment risk factor value and / or the driver behavior risk factor value and / or the driver sitting posture risk factor value.

[0027] Optionally, before inputting the driver response parameter into the driver status assessment model to obtain the driver status comprehensive score, the method further includes:

[0028] Constructing the driver status assessment model;

[0029] The formula of the driver status assessment model is:

[0030]

[0031] C is the comprehensive score of the driver status; z is the number of evaluation dimensions, and z is a positive integer; S i is the score of the driver's response in the i-th evaluation dimension, where i is a positive integer less than or equal to z; i is the weight coefficient of the i-th evaluation dimension;

[0032] The S i The calculation method is:

[0033]

[0034] The P std is a standard driver model parameter matrix, the standard driver model parameter matrix includes all the driver response parameters P obtained when the driver responds to the driver status check task; n is the total number of the response parameters, and n is a positive integer; P m is the mth response parameter, where m is a positive integer less than or equal to n; std,m is the mth response parameter in the standard driver model parameter matrix; i,m is the preset consistency index for the mth response parameter on the ith evaluation dimension.

[0035] Optionally, after inputting the driver response parameter into the driver status assessment model to obtain a comprehensive driver status score, the method further includes:

[0036] Determining the current takeover capability level of the driver according to the comprehensive score of the driver status;

[0037] The driver's current takeover capability level is fed back.

[0038] In a second aspect, the present application provides a driver status confirmation device based on automatic driving, comprising:

[0039] A first acquisition module, used to acquire the driving condition of the vehicle in real time when the vehicle is in an automatic driving state;

[0040] An input module, used for inputting the driving situation into the trigger rule model to obtain a comprehensive risk value;

[0041] A second acquisition module is used to acquire the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold when the comprehensive risk value exceeds the comprehensive risk threshold;

[0042] A calling module, used to call a preset driver status check action library using the type of risk factor to obtain a driver status check task;

[0043] A determination module is used to determine the driver status by executing the driver status check task.

[0044] Optionally, the determining module includes:

[0045] An execution unit, configured to execute the driver status checking task;

[0046] A collection unit, used for collecting the driver's response operation to the driver status check task to obtain a driver response parameter;

[0047] An input unit is used to input the driver response parameter into the driver status assessment model to obtain a comprehensive driver status score.

[0048] Optionally, the device further comprises:

[0049] A construction module, used for constructing the trigger rule model;

[0050] The formula of the trigger rule model is:

[0051] T=η a R env +η b R beh +η c R pos ;

[0052] T is the comprehensive risk value, Renv is the external road environment risk factor, the R beh is the driver behavior risk factor, the R pos is the driver's sitting posture risk factor, the η a is the weight coefficient of the external road environment risk factor, and the η b is the weight coefficient of the driver behavior risk factor, and the η c is the weight coefficient of the driver's sitting posture risk factor.

[0053] Optionally, the input unit includes:

[0054] An input subunit, used to input the driving situation into the trigger rule model; the driving situation includes positioning data, traffic environment information, navigation map prompt information, real-time driving behavior data and driver seat status information;

[0055] A first setting subunit is used for setting the external road environment risk factor to true if the positioning data, the traffic environment information and the navigation map prompt information meet the setting condition of the external road environment risk factor, so as to obtain the external road environment risk factor value;

[0056] A second setting subunit is used for setting the driver behavior risk factor to true if the real-time driving behavior data meets the driver behavior risk factor setting condition, so as to obtain the driver behavior risk factor value;

[0057] A third setting subunit is used for setting the driver's sitting posture risk factor to true if the driver's seat state information meets the driver's sitting posture risk factor setting condition, so as to obtain the driver's sitting posture risk factor value;

[0058] The determination subunit is used to determine the comprehensive risk value by using the external road environment risk factor value and / or the driver behavior risk factor value and / or the driver sitting posture risk factor value.

[0059] Optionally, the device further comprises:

[0060] A construction subunit, used for constructing the driver state assessment model;

[0061] The formula of the driver status assessment model is:

[0062]

[0063] C is the comprehensive score of the driver status; z is the number of evaluation dimensions, and z is a positive integer; S i is the score of the driver's response in the i-th evaluation dimension, where i is a positive integer less than or equal to z;i is the weight coefficient of the i-th evaluation dimension;

[0064] The S i The calculation method is:

[0065]

[0066] The P std is a standard driver model parameter matrix, the standard driver model parameter matrix includes all the driver response parameters P obtained when the driver responds to the driver status check task; n is the total number of the response parameters, and n is a positive integer; P m is the mth response parameter, where m is a positive integer less than or equal to n; std,m is the mth response parameter in the standard driver model parameter matrix; i,m is the preset consistency index for the mth response parameter on the ith evaluation dimension.

[0067] Optionally, the device further comprises:

[0068] A determination unit, configured to determine the current takeover capability level of the driver according to the comprehensive score of the driver status;

[0069] A feedback unit is used to provide feedback on the driver's current takeover capability level.

[0070] In a third aspect, an embodiment of the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor; when the processor executes the computer program, it implements a driver status confirmation method based on automatic driving as described in any one of the implementation methods in the first aspect of the embodiment of the present application.

[0071] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes a driver status confirmation method based on automatic driving as described in any one of the implementation methods in the first aspect of the embodiment of the present application.

[0072] The present application provides a driver status confirmation method based on automatic driving. When executing the method, first, when the vehicle is in the automatic driving state, the driving condition of the vehicle is obtained in real time, and then the driving condition is input into the trigger rule model to obtain a comprehensive risk value. Then, when the comprehensive risk value exceeds the comprehensive risk threshold, the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold is obtained. Then, the type of risk factor is used to call the preset driver status check action library to obtain the driver status check task. Finally, the driver status is determined by executing the driver status check task. In this way, the driver status check task is determined by the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold, and the driver status is determined by executing the driver status check task, so that the driver status can be accurately confirmed in automatic driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0074] Figure 1 A flowchart of a driver status confirmation method based on automatic driving provided in an embodiment of the present application;

[0075] Figure 2 A schematic diagram of the structure of a driver status confirmation device based on automatic driving provided in an embodiment of the present application;

[0076] Figure 3 A computer device is provided in an embodiment of the present application. DETAILED DESCRIPTION

[0077] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. The present application provides a driver status confirmation method and device based on automatic driving, which is used in the field of automatic driving technology. The above is only an example and does not limit the application field of the method and device name provided in the present application.

[0078] The autonomous driving system is responsible for controlling the vehicle. The driver does not need to pay attention to the road ahead for a long time and can perform other tasks during driving. However, when the system cannot handle a situation, the driver must control the vehicle within a limited time. During the process of taking over the driving rights, if the driver is not ready, it is very easy to cause a traffic accident due to human error. Therefore, during the process of autonomous driving, how to efficiently confirm the driver's status and evaluate the driver's ability to complete the driving task, so as to provide reference for the autonomous driving system and decide whether to transfer the driving rights, is one of the key technical issues for the safe operation of autonomous driving vehicles.

[0079] In the prior art, the driver's facial expression, eye focus and eye closure are obtained to confirm whether the driver is paying attention to the road ahead. However, since the driver does not need to pay attention to the road ahead for a long time in the state of automatic driving, the confirmation of the driver's state is not accurate.

[0080] After research, the inventor proposed the technical solution of this application. When executing the method, first, when the vehicle is in the automatic driving state, the driving situation of the vehicle is obtained in real time, and then the driving situation is input into the trigger rule model to obtain a comprehensive risk value. Then, when the comprehensive risk value exceeds the comprehensive risk threshold, the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold is obtained. Then, the preset driver status check action library is called using the type of risk factor to obtain the driver status check task. Finally, the driver status is determined by executing the driver status check task. In this way, the driver status check task is determined by the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold, and the driver status is determined by executing the driver status check task, so that the driver status can be accurately confirmed in automatic driving.

[0081] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. It should be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0082] See also Figure 1 , Figure 1 A flowchart of a driver status confirmation method based on automatic driving provided in an embodiment of the present application includes:

[0083] S101: When the vehicle is in an automatic driving state, obtain the driving condition of the vehicle in real time.

[0084] Autonomous driving is divided into six levels, from L0 to L5. In L3 autonomous driving, the autonomous driving system is responsible for controlling the vehicle. The driver does not need to pay attention to the road ahead for a long time and can do other tasks during driving. However, when the system cannot handle a situation, the driver must control the vehicle within a limited time. During the process of taking over driving rights, if the driver is not ready, it is very easy to cause a traffic accident due to human error.

[0085] Therefore, when the vehicle is in L3 level autonomous driving state, it is necessary to obtain the vehicle's driving conditions in real time, where the driving conditions include but are not limited to positioning data, traffic environment information, navigation map prompt information, real-time driving behavior data and driver's seat status information.

[0086] S102: Input the driving situation into the trigger rule model to obtain a comprehensive risk value.

[0087] Before executing step S102, it is necessary to construct a trigger rule model, which can comprehensively consider the real-time external road environment risk, driver behavior risk and driver sitting posture risk of the vehicle during the automatic driving process, and output the comprehensive risk T. The calculation method of the comprehensive risk T of the trigger rule model is as follows:

[0088] T=η a R env +η b R beh +η c R pos ;

[0089] Among them, T is the comprehensive risk value; R env is the external road environment risk factor; R beh is the driver behavior risk factor; R pos is the driver's sitting posture risk factor; η a is the weight coefficient of the external road environment risk factor; η b is the weight coefficient of the driver behavior risk factor; η c is the weight coefficient of the driver's sitting posture risk factor. The weight coefficient of the external road environment risk factor, the weight coefficient of the driver's behavior risk factor and the weight coefficient of the driver's sitting posture risk factor are pre-set weight coefficients.

[0090] If the positioning data, traffic environment information and navigation map prompt information meet the external road environment risk factor setting conditions, the external road environment risk factor is set to true, wherein the external road environment risk factor setting conditions can be formulated by technicians in this field based on experience, and a large and comprehensive table can be prepared in advance based on statistical data, which defines in detail all road environments and the risk factor values ​​corresponding to each environment. For example: if the real-time navigation map prompts that there is a high-accident section ahead, and the real-time positioning data indicates that the distance to the high-accident section is 300m, the external road environment risk factor is set to true.

[0091] If the real-time driving behavior data meets the driver behavior risk factor setting condition, the driver behavior risk factor is set to true. Among them, the driver behavior risk factor setting condition can be to compare the real-time driving behavior data with the preset behavior threshold value that is not suitable for driving. When the real-time driving behavior data meets the behavior threshold value that is not suitable for driving, the driver behavior risk factor is set to true, wherein the preset behavior threshold value that is not suitable for driving is determined in advance based on historical driving behavior big data. For example: the preset behavior threshold value that is not suitable for driving is that the driver operates the entertainment screen 6 times continuously within 5 seconds. When the number of operation information received by the entertainment screen within 5 seconds reaches 6 times, the driver behavior risk factor is set to true.

[0092] If the driver's seat status information meets the driver's sitting posture risk factor setting condition, the driver's sitting posture risk factor is set to true. Among them, the driver's sitting posture risk factor setting condition can be formulated by technical personnel in this field based on experience, and a large and comprehensive table can be prepared in advance based on statistical data, in which all driver sitting postures and the risk factor values ​​corresponding to each driver sitting posture are defined in detail. For example: when the driver's seat back tilt exceeds 45 degrees (the driver's seat back is considered to be 0 degrees when it is vertical to the seat), the driver's sitting posture risk factor is set to true.

[0093] Finally, a comprehensive risk value is calculated using the external road environment risk factor value and / or the driver behavior risk factor value and / or the driver sitting posture risk factor value.

[0094] S103: When the comprehensive risk value exceeds the comprehensive risk threshold, the type of risk factor causing the comprehensive risk to exceed the comprehensive risk threshold is obtained.

[0095] Determine whether the comprehensive risk value calculated in S102 is greater than the comprehensive risk threshold, wherein the comprehensive risk threshold is set in advance by technical personnel in this field according to specific circumstances. When the comprehensive risk value is greater than the comprehensive risk threshold, it indicates that the traffic environment is complex or the driver is negligent. At this time, obtain the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold. For example, when calculating the comprehensive risk value, only the driver's sitting posture risk factor is set to true, then the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold is determined to be the driver's sitting posture risk factor; when calculating the comprehensive risk value, both the external road environment risk factor and the driver's behavior risk factor are set to true, then the types of risk factors that cause the comprehensive risk to exceed the comprehensive risk threshold are determined to be the external road environment risk factor and the driver's behavior risk factor, which are not listed one by one here.

[0096] S104: Using the type of risk factor, a preset driver status check action library is called to obtain a driver status check task.

[0097] The preset driver status check action library is called according to the type of risk factor to obtain the driver status check task. For example, when the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold is the driver sitting posture risk factor, the driver status check task obtained by calling the preset driver status check action library is to let the driver straighten the seat back; when the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold is the external road environment risk factor, the driver status check task obtained by calling the preset driver status check action library is to let the driver hold the steering wheel for 10 seconds. The following are not listed one by one here.

[0098] S105: Determine the driver status by executing the driver status check task.

[0099] Execute the driver status check task obtained in S104, and collect the driver's response operation to the driver status check task to obtain the driver response parameters, wherein the driver response parameters include but are not limited to the driver's reaction delay time, the accuracy of the driver's response action and the driver's action completion time. The driver response action and its collection equipment include but are not limited to: collecting the driver's voice through a microphone, reading the steering wheel hand torque through the vehicle bus, obtaining the pressing state of the button through the steering wheel button, and obtaining the backrest inclination of the driver's seat through the seat sensor. The above equipment is common equipment on the car and does not need to be configured separately. Then, the collected driver action is compared and judged with the action sequence required in the inspection task, so as to generalize the multimodal action parameters into a set of driver response parameters P of the same dimension, so as to reflect the driver's response to the inspection task in a description method of the same dimension. Among them, the multimodal action parameters include but are not limited to sound, action and button. The driver response parameter P is input into the driver state evaluation model to obtain the driver state comprehensive score to determine the driver state.

[0100] Before inputting the driver response parameters into the driver state evaluation model, it is necessary to construct the driver state evaluation model first, and input the driver response parameters P and the parameter matrix P corresponding to the standard driver model. std The consistency check can evaluate the scores of different evaluation dimensions such as driver sobriety, driver concentration, and driver agility in real time, and then build a multi-dimensional driver status evaluation model. Among them, the parameter matrix P corresponding to the standard driver model std These are all the driver response parameters obtained when completing the driver status check task based on the standard driver model.

[0101] Specifically, the calculation of the driver state by the driver state evaluation model can be formulated as:

[0102]

[0103] Among them, C is the comprehensive score of the driver's status; z is the number of evaluation dimensions, z is a positive integer; S i is the score of the driver's response in the i-th evaluation dimension, i is a positive integer less than or equal to z; η i is the weight coefficient of the ith evaluation dimension.

[0104] The calculation of the score of a certain evaluation dimension evaluated by consistency checking can be formulated as follows:

[0105]

[0106] Among them, P stdis the standard driver model parameter matrix, which includes all driver response parameters P obtained when the driver responds to the driver status check task; n is the total number of response parameters, n is a positive integer; P m is the mth response parameter, m is a positive integer less than or equal to n; P std,m is the mth response parameter in the standard driver model parameter matrix; K i,m is the preset consistency index for the mth response parameter on the ith evaluation dimension.

[0107] For example, if the driver's concentration is S1, the response parameters include the driver's reaction delay time, the accuracy of the driver's response action, and the driver's action completion time. The calculation method of the driver's concentration S1 is as follows:

[0108] Driver concentration

[0109]

[0110] Among them, the driver's reaction delay time can better reflect the driver's concentration. Therefore, the reaction delay time consistency index in the concentration evaluation will be significantly higher than the consistency index of the action accuracy and action completion time. Its specific value is determined according to the calibration results.

[0111] In some embodiments, after obtaining the comprehensive driver status score C, the driver's current takeover ability can be graded according to the comprehensive driver status score C. For example, the driver's current takeover ability can be graded into four levels: excellent, good, medium, and poor. Then, the obtained driver's current takeover ability level is fed back as a basis for decision-making on changes in driving behavior and safe handover of driving rights of the autonomous driving vehicle.

[0112] In the embodiment provided by the present application, when executing the method, first, when the vehicle is in the automatic driving state, the driving condition of the vehicle is obtained in real time, and then the driving condition is input into the trigger rule model to obtain a comprehensive risk value, and then, when the comprehensive risk value exceeds the comprehensive risk threshold, the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold is obtained, and then, the preset driver state check action library is called by the type of risk factor to obtain the driver state check task, and finally, the driver state is determined by executing the driver state check task. In this way, the driver state check task is determined by the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold, and the driver state is determined by executing the driver state check task, so that the driver state can be accurately confirmed in automatic driving.

[0113] The above are some specific implementations of the driver status confirmation method based on automatic driving provided by the embodiment of the present application. Based on this, the present application also provides a corresponding device. The device provided by the embodiment of the present application will be introduced from the perspective of functional modularization.

[0114] See also Figure 2 , Figure 2 A schematic diagram of a driver status confirmation device based on automatic driving provided in an embodiment of the present application is provided. The driver status confirmation device 200 based on automatic driving includes:

[0115] A first acquisition module 210, used to acquire the driving condition of the vehicle in real time when the vehicle is in an automatic driving state;

[0116] An input module 220, for inputting the driving situation into the trigger rule model to obtain a comprehensive risk value;

[0117] A second acquisition module 230 is used to acquire the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold when the comprehensive risk value exceeds the comprehensive risk threshold;

[0118] A calling module 240 is used to call a preset driver status check action library using the type of risk factor to obtain a driver status check task;

[0119] The determination module 250 is used to determine the driver status by executing the driver status check task.

[0120] Optionally, the determining module 250 includes:

[0121] An execution unit, configured to execute the driver status checking task;

[0122] A collection unit, used for collecting the driver's response operation to the driver status check task to obtain a driver response parameter;

[0123] An input unit is used to input the driver response parameter into the driver status assessment model to obtain a comprehensive driver status score.

[0124] Optionally, the device 200 further includes:

[0125] A construction module, used for constructing the trigger rule model;

[0126] The formula of the trigger rule model is:

[0127] T=η a R env +η b R beh +η c Rpos ;

[0128] T is the comprehensive risk value, R env is the external road environment risk factor, the R beh is the driver behavior risk factor, the R pos is the driver's sitting posture risk factor, the η a is the weight coefficient of the external road environment risk factor, and the η b is the weight coefficient of the driver behavior risk factor, and the η c is the weight coefficient of the driver's sitting posture risk factor.

[0129] Optionally, the input unit includes:

[0130] An input subunit, used to input the driving situation into the trigger rule model; the driving situation includes positioning data, traffic environment information, navigation map prompt information, real-time driving behavior data and driver seat status information;

[0131] A first setting subunit is used for setting the external road environment risk factor to true if the positioning data, the traffic environment information and the navigation map prompt information meet the setting condition of the external road environment risk factor, so as to obtain the external road environment risk factor value;

[0132] A second setting subunit is used for setting the driver behavior risk factor to true if the real-time driving behavior data meets the driver behavior risk factor setting condition, so as to obtain the driver behavior risk factor value;

[0133] A third setting subunit is used for setting the driver's sitting posture risk factor to true if the driver's seat state information meets the driver's sitting posture risk factor setting condition, so as to obtain the driver's sitting posture risk factor value;

[0134] The determination subunit is used to determine the comprehensive risk value by using the external road environment risk factor value and / or the driver behavior risk factor value and / or the driver sitting posture risk factor value.

[0135] Optionally, the device 200 further includes:

[0136] A construction subunit, used for constructing the driver state assessment model;

[0137] The formula of the driver status assessment model is:

[0138]

[0139] C is the comprehensive score of the driver status; z is the number of evaluation dimensions, and z is a positive integer; S i is the score of the driver's response in the i-th evaluation dimension, where i is a positive integer less than or equal to z; i is the weight coefficient of the i-th evaluation dimension;

[0140] The S i The calculation method is:

[0141]

[0142] The P std is a standard driver model parameter matrix, the standard driver model parameter matrix includes all the driver response parameters P obtained when the driver responds to the driver status check task; n is the total number of the response parameters, and n is a positive integer; P m is the mth response parameter, where m is a positive integer less than or equal to n; std,m is the mth response parameter in the standard driver model parameter matrix; i,m is the preset consistency index for the mth response parameter on the ith evaluation dimension.

[0143] Optionally, the device 200 further includes:

[0144] A determination unit, configured to determine the current takeover capability level of the driver according to the comprehensive score of the driver status;

[0145] A feedback unit is used to provide feedback on the driver's current takeover capability level.

[0146] The embodiments of the present application also provide corresponding devices and computer storage media for implementing the solutions provided by the embodiments of the present application.

[0147] like Figure 3 As shown, the computer device 01 is in the form of a general computing device. The components of the computer device 01 may include but are not limited to: one or more processors or processing units 03, a system memory 08, and a bus 04 connecting different system components (including the system memory 08 and the processing unit 03).

[0148] Bus 04 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0149] The computer device 01 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 01, including volatile and non-volatile media, removable and non-removable media.

[0150] The system memory 08 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 09 and / or cache memory 10. The computer device 01 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 11 may be used to read and write non-removable, non-volatile magnetic media ( Figure 3 not shown, usually called a "hard drive"). Although Figure 3 Not shown in the figure, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 04 via one or more data medium interfaces. The memory 08 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0151] A program / utility 12 having a set (at least one) of program modules 13 may be stored, for example, in the memory 08, such program modules 13 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include an implementation of a network environment. The program modules 13 generally perform the functions and / or methods of the embodiments described herein.

[0152] The computer device 01 can communicate with a display 07, and can also communicate with one or more external devices 02 (e.g., a keyboard, a pointing device, etc.), and can also communicate with one or more devices that enable a user to interact with the computer device 01, and / or communicate with any device that enables the computer device 01 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication can be performed through an input / output (I / O) interface 06. In addition, the computer device 01 can also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 05. Figure 3 As shown, the network adapter 05 communicates with other modules of the computer device 01 via the bus 04. It should be understood that although Figure 3 Not shown, other hardware and / or software modules may be used in conjunction with computer device 01, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0153] The processor unit 03 executes various functional applications and data processing by running the programs stored in the system memory 08, for example, implementing a baud rate adaptive program flashing method provided in an embodiment of the present application.

[0154] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0155] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0156] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0157] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A driver status confirmation method based on automatic driving, characterized in that: include: When the vehicle is in an automatic driving state, obtaining the driving condition of the vehicle in real time; Inputting the driving situation into the trigger rule model to obtain a comprehensive risk value; When the comprehensive risk value exceeds the comprehensive risk threshold, obtaining the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold; Using the type of risk factor, a preset driver status check action library is called to obtain a driver status check task; By executing the driver status check task, the driver status is determined.

2. The method according to claim 1, characterized in that The determining the driver status by executing the driver status checking task includes: Execute the driver status check task; Collecting the driver's response operation to the driver status check task to obtain a driver response parameter; The driver response parameters are input into the driver status assessment model to obtain a comprehensive driver status score.

3. The method according to claim 1, characterized in that Before inputting the driving situation into the trigger rule model to obtain a comprehensive risk value, the method further includes: Constructing the trigger rule model; The formula of the trigger rule model is: T=η a R env +n b R beh +n c R pos ; T is the comprehensive risk value, R env is the external road environment risk factor, the R beh is the driver behavior risk factor, the R pos is the driver's sitting posture risk factor, the η a is the weight coefficient of the external road environment risk factor, and the η b is the weight coefficient of the driver behavior risk factor, and the η c is the weight coefficient of the driver's sitting posture risk factor.

4. The method according to claim 3, characterized in that The step of inputting the driving situation into the trigger rule model to obtain a comprehensive risk value includes: Inputting the driving situation into the trigger rule model; the driving situation includes positioning data, traffic environment information, navigation map prompt information, real-time driving behavior data and driver seat status information; If the positioning data, the traffic environment information and the navigation map prompt information meet the external road environment risk factor setting condition, the external road environment risk factor is set to true to obtain the external road environment risk factor value; If the real-time driving behavior data meets the driver behavior risk factor setting condition, the driver behavior risk factor is set to true to obtain the driver behavior risk factor value; If the driver's seat state information satisfies the driver's sitting posture risk factor setting condition, the driver's sitting posture risk factor is set to true to obtain the driver's sitting posture risk factor value; The comprehensive risk value is determined using the external road environment risk factor value and / or the driver behavior risk factor value and / or the driver sitting posture risk factor value.

5. The method according to claim 2, characterized in that: Before inputting the driver response parameter into the driver status assessment model to obtain the driver status comprehensive score, the method further includes: Constructing the driver status assessment model; The formula of the driver status assessment model is: C is the comprehensive score of the driver status; z is the number of evaluation dimensions, and z is a positive integer; S i is the score of the driver's response in the i-th evaluation dimension, where i is a positive integer less than or equal to z; i is the weight coefficient of the i-th evaluation dimension; The S i The calculation method is: The P std is a standard driver model parameter matrix, the standard driver model parameter matrix includes all the driver response parameters P obtained when the driver responds to the driver status check task; n is the total number of the response parameters, and n is a positive integer; P m is the mth response parameter, where m is a positive integer less than or equal to n; std,m is the mth response parameter in the standard driver model parameter matrix; i,m is the preset consistency index for the mth response parameter on the ith evaluation dimension.

6. The method according to claim 2, characterized in that After inputting the driver response parameter into the driver status assessment model to obtain a comprehensive driver status score, the method further includes: Determining the current takeover capability level of the driver according to the comprehensive score of the driver status; The driver's current takeover capability level is fed back.

7. A driver status confirmation device based on automatic driving, characterized in that: include: A first acquisition module, used to acquire the driving condition of the vehicle in real time when the vehicle is in an automatic driving state; An input module, used for inputting the driving situation into the trigger rule model to obtain a comprehensive risk value; A second acquisition module is used to acquire the type of risk factor that causes the comprehensive risk to exceed the comprehensive risk threshold when the comprehensive risk value exceeds the comprehensive risk threshold; A calling module, used to call a preset driver status check action library using the type of risk factor to obtain a driver status check task; A determination module is used to determine the driver status by executing the driver status check task.

8. The device according to claim 7, characterized in that The determining module comprises: An execution unit, configured to execute the driver status checking task; A collection unit, used for collecting the driver's response operation to the driver status check task to obtain a driver response parameter; An input unit is used to input the driver response parameter into the driver status assessment model to obtain a comprehensive driver status score.

9. A computer device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for confirming the driver status based on automatic driving as described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes the driver status confirmation method based on automatic driving as described in any one of claims 1-6.

Images