Method for establishing sample bank for distinguishing driving state of driver

A driving state and establishment method technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as difficulty in obtaining driving state information, impossibility of real realization of dangerous driving state, etc.

Active Publication Date: 2017-02-01

XIAN UNIV OF SCI & TECH

0 Cites 2 Cited by

AI-Extracted Technical Summary

Problems solved by technology

Among them, the acquisition of driving state information when the driver is in a normal driving state is relatively simple, and the monitoring device can be used to monitor the driving state information of the driver during the driving process; however, the...

Abstract

The invention discloses a method for establishing a sample bank for distinguishing driving states of a driver. The method comprises the following steps: I, acquiring driving state information in a normal driving state, namely, monitoring driving state information of a vehicle driven by a monitored driver according to a route designed in advance by using a driving state information monitoring device according to monitoring frequency designed in advance, so as to obtain driving state information of multiple monitoring moments; II, confirming parameters of a vehicle kinetic model; III, acquiring driving state information in a dangerous driving state, namely, generating random numbers, screening the random numbers, acquiring a driver response time array, and acquiring the driving state information; IV, establishing the sample bank. The method disclosed by the invention is simple in step, reasonable in design, convenient to implement and good in use effect, sample information in the dangerous driving state can be acquired by collecting the driving state information in the normal driving state, and the difficulty in acquiring the driving state information in the dangerous driving state can be effectively solved.

Application Domain

Special data processing applicationsInformatics

Technology Topic

Driver/operatorInformation monitoring +5

Image

Examples

Experimental program(1)

Example Embodiment

[0053] like figure 1 A method for establishing a sample library for driver driving state identification is shown, including the following steps:

[0054] Step 1. Obtaining the driving status information under normal driving conditions: using the driving status information monitoring device 1 and monitoring the driving status information of the vehicle driven by the monitored driver according to the pre-designed route according to the pre-designed monitoring frequency, and synchronously transmit the monitored information to the data processor 2 to obtain the driving state information at multiple monitoring moments;

[0055] The driving state information monitoring device 1 includes a steering wheel angle detection unit 1-1 for detecting the steering wheel angle of the driven vehicle, and a lateral acceleration detection unit 1-2 for detecting the lateral acceleration of the driven vehicle. The rotation angle detection unit 1-1 and the lateral acceleration detection unit 1-2 are both connected to the data processor 2; the driving state information at each monitoring moment includes the steering wheel rotation angle and the lateral direction detected by the steering wheel rotation angle detection unit 1-1 at that moment. the lateral acceleration detected by the acceleration detection unit 1-2;

[0056] Step 2: Determination of vehicle dynamics model parameters: the data processor 2 obtains the steering wheel angle function δ according to the driving state information at multiple monitoring moments obtained in step 1 sw (t) and the lateral acceleration function where δ sw (t) is the function of the time-varying steering wheel angle of the vehicle driven in the driving process in step 1, is the function of the lateral acceleration of the vehicle driven in the driving process in step 1 over time; the data processor 2 is based on the formula Combined with the transfer function of the vehicle dynamics model of the vehicle driven by the monitored driver in step 1 For the vehicle dynamics model parameter G ay , T y1 , T y2 , T 1 and T 2 to be determined separately;

[0057] In formula (2), δ sw (s) is the steering wheel angle function δ sw The Laplace transform of (t), is the lateral acceleration function Laplace transform of ;

[0058] Step 3. The process of obtaining the driving state information in the dangerous driving state is as follows:

[0059] Step 301, random number generation: use the data processor 2 and call the random number generation module to generate a neural response time random array or an action response time random array;

[0060] The neural response time random array is a set of average numbers generated by calling the random number generation module, which is t d0 and the variance is σ d A random number of ; where t d0 =0.25~0.5; when the monitored driver is a male driver, σ d7.5; when the monitored driver is a female driver, σ d8;

[0061] The action response time random array is a set of average numbers generated by calling the random number generation module, which is T h0 and the variance is σ h A random number of ; where T h0 =0.12~0.2; when the monitored driver is a male driver, σ h2.6; when the monitored driver is a female driver, σ d1.95;

[0062] Step 302, random number screening: first determine the threshold N according to the preset fatigue degree tm , using the data processor 2 to calculate the neural reaction time judgment threshold t dm or action response time judgment threshold T hm , where N tm =0.7~0.9; Then according to the calculated t dm or T hm , screen the neural reaction time random array or the action reaction time random array generated in step 301 to obtain the neural reaction time array or the action reaction time random array in the dangerous driving state; the neural reaction time array in the Including a plurality of random numbers of the neural reaction time in the dangerous driving state, and the action reaction time random array includes a plurality of random numbers of the action reaction time in the dangerous driving state; t in the formula (3) da and t db are the upper limit and lower limit of the monitored driver's neural reaction time obtained from the pre-test, respectively, T in formula (4) ha and T hb are the upper limit and lower limit of the reaction time of the monitored driver's action obtained from the pre-test, respectively, t dm , T hm , t da , t db , T ha and T hb The unit is s;

[0063] When screening the random array of neural reaction times, according to the calculated t dm , using the data processor 2 to judge each random number in the random array of neural response time respectively; when judging any random number in the random array of neural response time, judge whether the random number is greater than t dm , and when the random number > t dm When , it is determined that the random number is the random number of the neural reaction time in the dangerous driving state;

[0064] When screening the random array of the action reaction time, according to the calculated T hm , using the data processor 2 to judge each random number in the random array of the action response time respectively; when judging any random number in the random array of the action response time, judge whether the random number is greater than T hm , and when the random number > T hm When , it is judged that the random number is the random number of the action reaction time in the dangerous driving state;

[0065] Step 303, driver reaction time array acquisition: use data processor 2 to perform time data pair calculation on the neural reaction time array or the action reaction time random array in step 302, and obtain the driver reaction time array; The reaction time array includes a plurality of driver reaction time data pairs in the dangerous driving state, and each of the driver reaction time data pairs includes a neural reaction time and an action reaction time;

[0066] Wherein, when the time data pair calculation is performed on the neural response time array, the data processor 2 is used to perform time data pair calculation on each random number in the neural response time array; a random number t di When calculating the time data pair, first use the formula Calculate the neural response time t di Corresponding fatigue degree N ti; then according to the formula Calculate the neural response time t di Corresponding action reaction time T hi , the t di and T hi Form a pair of driver reaction time data; i is a positive integer and i = 1, 2, ..., N d , N d is the total number of random numbers included in the neural response time array;

[0067] When the time data pair calculation is performed on the action response time array, the data processor 2 is used to calculate the time data pair for each random number in the action response time array respectively; any random number in the action response time array is randomly number t di When calculating the time data pair, first use the formula Calculate the action reaction time T hj Corresponding fatigue degree N tj; then according to the formula Calculate the action reaction time T hj Corresponding neural response time t dj , the t dj and T hj Form a pair of driver reaction time data; j is a positive integer and j = 1, 2, ..., N h , N h is the total number of random numbers included in the action response time array;

[0068] Step 304, acquisition of driving state information: According to the pre-established driver model, the data processor 2 is used to calculate the driving state information for the plurality of pairs of the driver response time data in the driver response time array described in step 303, respectively. , get N k Set the driving state information in the dangerous driving state; among them, N k is a positive integer and is the total number of driver reaction time data pairs included in the driver reaction time array, N k =N d or N h;

[0069] In step 1, the positions of the vehicles driven by the monitored drivers at a plurality of the monitoring moments are all monitoring positions, and each group of driving state information under the dangerous driving state includes a plurality of steering wheel angle signals under the dangerous driving state, The plurality of steering wheel angle signals are respectively the steering wheel angle signals of the vehicle driven by the monitored driver at a plurality of different monitoring positions in a dangerous driving state;

[0070] The input of the driver model is as described in step 2 The output is the function of the steering wheel angle of the vehicle being driven by the monitored driver according to the route pre-designed in step 1 under the dangerous driving state. The transfer function of the driver model is: In formula (9), T p , t d and T h are the preview time, neural reaction time and action reaction time of the monitored driver at the same moment during the driving process;

[0071]When using the data processor 2 to calculate the driving state information for any one of the driver reaction time data pairs in the driver reaction time array in step 303, according to formula (9), combined with the multiple data obtained in step 1 The lateral acceleration at each monitoring moment and the neural reaction time and action reaction time in the driver's reaction time data pair are obtained, and the vehicle driven by the monitored driver under the dangerous driving state corresponding to the driver's reaction time data pair is obtained. Steering wheel angle signals at different monitoring positions;

[0072] Step 4: Establishing a sample library: using the data processor 2 to establish a sample library, two types of samples are stored in the established sample library. The steering wheel angle signal at the monitoring time, another type of sample is a dangerous driving state sample, and this type of sample includes a plurality of steering wheel angle signals obtained in step 304 under the dangerous driving state.

[0073] In this embodiment, when calculating the transfer function V(s) of the vehicle dynamics model described in step 2, the δ sw (t) and Laplace transform is performed separately to get For simplicity of calculation

[0074] Therefore, when the transfer function V(s) of the vehicle dynamics model is calculated, the calculation process of the transfer function V(s) is a conventional transfer function calculation process, and the transfer function V(s) of the vehicle dynamics model is calculated. ) is the transfer function of the conventional vehicle dynamics model.

[0075] Among them, the vehicle dynamics model parameter G ay , T y1 , T y2 , T 1 and T 2 The model of the vehicle is related to the speed of the vehicle. And, G ay is the steady state gain of the vehicle dynamics model and where V is the driving speed of the vehicle, l is the wheelbase of the vehicle, and K is the stability factor of the vehicle, which is related to the model of the vehicle; where a and b are the distances from the center of mass of the vehicle to the front and rear axles of the vehicle, respectively, I z is the moment of inertia of the vehicle around the Z axis (ie the vertical direction), C 1 and C 2 are the sideslip coefficients of the front and rear wheels of the vehicle, respectively, T 2 =0.

[0076] In this embodiment, the driving state information monitoring device 1 in step 1 further includes a displacement detection unit 1-3 that detects the displacement of the driven vehicle in real time, and the displacement detection unit 1-3 is connected to the data processor 2;

[0077] In step 1, the driving state information at each monitoring time also includes the displacement detected by the displacement detection unit 1-3 at that time;

[0078] In step 1, before obtaining the driving state information under the normal driving state, first establish a plane rectangular coordinate system; the displacement detection unit 1-3 includes an X-axis direction displacement detection unit that detects the displacement of the driven vehicle in the X-axis direction. and a Y-axis direction displacement detection unit for detecting the displacement of the driven vehicle in the Y-axis direction, the X-axis direction displacement detection unit and the Y-axis direction displacement detection unit are both arranged on the center of mass of the driven vehicle.

[0079] In this embodiment, before obtaining the driving state information in the dangerous driving state in step 304, the data processor 2 is used to obtain the road curvature ρ at multiple different monitoring positions in the route pre-designed in step 1 p;

[0080] In step 304, when calculating the steering wheel angle of the vehicle driven by the monitored driver at a plurality of different monitoring positions in the dangerous driving state corresponding to the driver's reaction time data pair, according to formula (9), combined with step 1. The lateral acceleration at the monitoring position, the road curvature ρ at the monitoring position obtained from p And the nerve reaction time and action reaction time in this driver's reaction time data pair are calculated; In formula (9), In formula (10), K p is the correction factor and K p =110~150, ρ p is the road curvature at the monitoring location, is the optimal preview time corresponding to the driver's reaction time data pair and In formula (11), t d and T h are the neural reaction time and the action reaction time in the driver's reaction time data pair, respectively.

[0081] The actual road curvature ρ at a number of different monitoring locations in the pre-designed route p During the calculation, the pre-designed route is the ideal route obtained by the actual road after image preprocessing, and the road curvature at different monitoring positions is determined by ρ. p It is obtained by processing the road image information obtained by the front camera on the vehicle.

[0082] For simplicity of calculation, the pre-designed route in step 1 is a straight-line route or an arc-shaped route, and the road curvatures at multiple different monitoring positions in the pre-designed route are all the same. That is, the route of the actual road is a straight route or a circular arc route.

[0083] Among them, when the pre-designed route is a straight route, the road curvature at multiple different monitoring locations is zero; the pre-designed route is a circular route, and the road curvature at multiple different monitoring locations is R is the radius of the circular route.

[0084] In this embodiment, the lateral acceleration detection unit 1-2 in step 1 is arranged on the center of mass of the driven vehicle.

[0085] In actual use, the lateral acceleration detection unit 1-2 may not be arranged on the center of mass of the driven vehicle. According to the positional relationship between the lateral acceleration detection unit 1-2 and the center of mass of the driven vehicle, the lateral acceleration detection The measurements from unit 1-2 are scaled to yield the lateral acceleration at the centre of mass of the driven vehicle.

[0086] In this embodiment, the driving state information at M monitoring moments is obtained in step 1, where M is a positive integer and M≥50, and the number of the normal driving state samples stored in the sample library in step 4 is M, Each of the normal driving state samples is the steering wheel angle signal at a monitoring moment obtained in step 1; the number of the dangerous driving state samples stored in the sample library in step 4 is not less than M, and each The dangerous driving state samples are all a steering wheel angle signal obtained in step 304 under the dangerous driving state.

[0087] In this embodiment, when the data processor 2 is used in step 304 to calculate the driving state information for any one of the driver's reaction time data pairs in the driver's reaction time array, the data pair with the driver's reaction time data is obtained. The steering wheel angle signals of the vehicle driven by the monitored driver at M different monitoring positions in the corresponding dangerous driving state; N k The driving state information in the dangerous driving state includes the N in the dangerous driving state. k ×M of the steering wheel angle signals.

[0088] In addition, the number of the dangerous driving state samples stored in the sample database in step 4 is M to N k ×M pieces.

[0089] In this embodiment, the driving state information monitoring device 1 in step 1 further includes a sideslip angle detection unit 1-4 that detects the sideslip angle of the driven vehicle in real time. The sideslip angle detection unit 1-4 is connected to The data processor 2 is connected; the sideslip angle detection units 1-4 are arranged on the center of mass of the driven vehicle;

[0090] In step 1, the driving state information at each monitoring moment further includes the sideslip angle detected by the sideslip angle detection unit 1-4 at that moment.

[0091] In this embodiment, the driving state information monitoring device 1 in step 1 is a monitoring device that comes with the driven vehicle, and the driving state information monitoring device 1 is connected to the ECU controller of the driven vehicle; the data processor 2 Connected with the ECU controller, the driving state information monitoring device 1 is connected with the data processor 2 through the ECU controller.

[0092] Therefore, the actual wiring is very simple.

[0093] In this embodiment, N described in step 302 tm = 0.8.

[0094] In actual use, according to specific needs, the N tm The size of the value is adjusted accordingly.

[0095] Reaction time (RT) is referred to as reaction time, which refers to the time required from receiving a stimulus to the body making a reaction action, that is, the time interval from the stimulus to the response. The stimulation causes the activity of the sensory organs, which is transmitted to the brain through the nervous system, processed, and then transmitted from the brain to the effector, which acts on some external object. The response time is also called the response latency, which includes the time required by the sensory organs, the time consumed by the brain processing, the time of nerve conduction and the time of muscle response. Therefore, the response time mainly reflects the coordination and rapid response ability of the human nervous and muscular system.

[0096] The reaction includes 3 phases. The first phase: the time when the stimulation causes the receptors to induce nerve impulses and transmit them to the neurons in the brain; the second phase: the nerve impulses are transmitted from the sensory neurons to the sensory and motor centers of the cerebral cortex, and then from the center to the motor nerves. The time of the effector; the third phase: the time when the effector receives the impulse to cause the movement. The sum of the above three times is the reaction time. The neural response time described in the present invention is the sum of the first two times mentioned above, that is, the time when the stimulation causes the receptors to induce nerve impulses and transmit them to the cerebral neurons and the time when the nerve impulses are transmitted from the sensory neurons to the sensory and motor centers of the cerebral cortex. , and the sum of the time from the central nervous system to the effector organs. The action reaction time mentioned in the present invention refers to the above-mentioned third time, that is, the time when the effector receives the impulse to cause movement.

[0097] Simple response time refers to the time interval between when a stimulus is presented and the subject is required to respond immediately from seeing or hearing the stimulus; also known as A-time.

[0098] In this embodiment, when the monitored driver's reaction time is tested, a conventional simple reaction time test method is adopted, and a visual reaction time test method is adopted, that is, the used stimulus is a visual stimulus.

[0099] And, according to the test result of the monitored driver's reaction time, for the t described in step 302 da , t db , T ha and T hb to be determined separately.

[0100] In this embodiment, the neural reaction time measuring instrument is used to measure the t in step 302. da and t db Test separately.

[0101] At the same time, combined with the test results of the monitored driver's reaction time, combined with the t obtained from the test da and t db , for T described in step 302 ha and T hb to be determined separately.

[0102]In actual use, in the test results of the monitored driver's reaction time, the reaction time obtained by the test is the sum of the monitored driver's neural reaction time and action reaction time. At the same time, during the reaction time test, a neural reaction time meter is used to test the neural reaction time of the monitored driver, and the action reaction time of the monitored driver is tested accordingly. In this way, through multiple tests, t described in step 302 can be obtained da , t db , T ha and T hb.

[0103] In this embodiment, the monitoring frequency described in step 1 is 5 Hz. In actual use, the monitoring frequency can be adjusted accordingly between 3 Hz and 10 Hz according to specific needs.

[0104] The above are only preferred embodiments of the present invention and do not limit the present invention. Any simple modifications, changes and equivalent structural changes made to the above embodiments according to the technical essence of the present invention still belong to the technology of the present invention. within the scope of the program.

PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.