CN115946710B - Driving characteristic data processing method, device and storage medium - Google Patents
Driving characteristic data processing method, device and storage medium Download PDFInfo
- Publication number
- CN115946710B CN115946710B CN202310241023.0A CN202310241023A CN115946710B CN 115946710 B CN115946710 B CN 115946710B CN 202310241023 A CN202310241023 A CN 202310241023A CN 115946710 B CN115946710 B CN 115946710B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- distribution
- lane
- driving
- steering
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 17
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000009826 distribution Methods 0.000 claims description 127
- 238000000034 method Methods 0.000 claims description 37
- 238000004590 computer program Methods 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 13
- 230000000694 effects Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 208000003443 Unconsciousness Diseases 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Traffic Control Systems (AREA)
Abstract
The application discloses a driving characteristic data processing method, a driving characteristic data processing device and a storage medium, which are used for reducing the false alarm rate. The driving characteristic data processing method disclosed by the application comprises the following steps: extracting the traffic flow motion characteristics of the side lanes; extracting driving characteristics based on a single driving simulator; and determining the left boundary steering angle and/or the right boundary steering angle of the steering wheel corner of the driver without obvious steering intention according to the side lane traffic flow motion characteristics and the driving characteristics. The application also provides a driving characteristic data processing device and a storage medium.
Description
Technical Field
The present disclosure relates to the field of driving feature data processing, and in particular, to a driving feature data processing method, device and storage medium.
Background
Lane keeping assist systems have become one of the key technologies for current intelligent driving as a safety-assist driving technology for keeping a vehicle safely in a lane by applying an assist torque to a steering wheel. However, the existing lane keeping assist system mainly focuses on the deviation degree of the vehicle relative to the lane line, and does not consider the driving habit of the driver and the influence of surrounding traffic flow on the danger caused by the deviation of the vehicle, so that the problems of high false alarm rate, excessive intervention degree and the like are caused.
Disclosure of Invention
In view of the above technical problems, embodiments of the present application provide a driving feature data processing method, device, and storage medium, which are used for reducing the false alarm rate.
In a first aspect, a driving feature data processing method provided in an embodiment of the present application includes:
extracting the traffic flow motion characteristics of the side lanes;
extracting driving characteristics based on a single driving simulator;
and determining the left boundary steering angle and/or the right boundary steering angle of the steering wheel corner of the driver without obvious steering intention according to the side lane traffic flow motion characteristics and the driving characteristics.
Preferably, the extracting the side lane traffic flow movement feature includes:
extracting position information data of a side lane vehicle;
preprocessing the position information data of the side lane vehicle;
performing normal distribution fitting on position information data of different lanes;
and determining the traffic flow motion characteristics of the side lanes according to the normal distribution fitting.
Preferably, the position information data of the side-lane vehicle includes:
Wherein, for the lateral position of the geometric center of the vehicle detected by the lidar,/-for>For the longitudinal position of the geometric center of the vehicle detected by the laser radar, i is the data number, i is more than or equal to 1 and less than or equal to n, and n is the total number of data acquired from a real road.
The preprocessing of the position information data of the side-lane vehicle comprises the following steps:
converting a coordinate system, namely converting data under a sensor coordinate system acquired by a laser radar into data under a geodetic coordinate system where a lane line is located;
estimating the position of the lane line to obtain the distance between the center of the vehicle and the lane line on the left side;
Preferably, the said movement characteristics according to the said side-road traffic flow include one or a combination of the following:
distributing probabilities in lanes by the geometric center of the vehicle;
the probability of the vehicle being distributed on the right lane line;
the probability of the distribution of the vehicle on the left lane line;
the distribution probability of the vehicles in the deviated distance when the vehicles deviate leftwards;
the probability of vehicle distribution within the offset distance when the vehicle is offset to the right.
Specifically, the probability of the distribution of the geometric center of the vehicle in the lane is that;
When the vehicle deviates leftwards, the distribution probability of the vehicle in the deviation distance is as follows:
the vehicle distribution probability in the deviated distance when the vehicle deviates rightward is as follows:
wherein s is the transverse distance between the geometric center of the vehicle and the left/right lane line, and comprisesAnd,for the distance between the center of the vehicle and the lane line on the right side,is thatIs used for the average value of (a),is thatIs a function of the variance of (a),d is the lane width, and N () is the probability density function normal distribution sign, which is the distance between the center of the vehicle and the lane line on the left side.
Preferably, the extracting the driving characteristics based on the single-person driving simulator includes:
performing off-state distribution fitting on the transverse position of the vehicle to obtain distribution;
Deleting data of the vehicle deviating from the driver's preferred driving position;
steering wheel angle in processed data setNormal distribution fitting is carried out to obtain the distribution characteristics of the steering angle of the vehicle;
Wherein the method comprises the steps ofFor the distance between the center of the vehicle and the left lane line,to fit the driver's preferred lateral position when controlling the vehicle to travel within the lane,to fit the vehicle lateral position variance.For steering angle of driver during unintentional steeringThe distribution center is provided with a plurality of distribution holes,the variance of steering wheel angle distribution at the time of the unintentional steering is fitted.
Further, performing a bias distribution fitting on the lateral position of the vehicle to obtain a distribution center includes:
performing a third-order process on the lateral position of the vehicle;
and (5) performing normal distribution fitting.
The deleting the data of the vehicle deviating from the driver's preferred driving position includes:
Preferably, the performing normal distribution fitting on the steering wheel angle in the processed data set to obtain the vehicle steering angle distribution feature includes:
and carrying out normal distribution fitting on all steering wheel rotation angle data in the data after deleting the data of the vehicle which deviates from the driving position preferred by the driver.
Preferably, the determining the left and/or right boundary steering angle of the steering wheel corner of the driver without obvious steering intention according to the side-lane traffic flow motion characteristic and the driving characteristic comprises:
the left boundary steering angle of the steering wheel angle of the driver without obvious steering intention is as follows:
the right boundary steering angle of the steering wheel angle of the driver without obvious steering intention is:
wherein the method comprises the steps ofTo fit the steering angle distribution center when the driver is unintentionally steering,to fit the steering wheel angle distribution variance at unintended steering, SW is the vehicle steering wheel angle.
In a second aspect, embodiments of the present application further provide a driving feature data processing apparatus, including:
the first feature extraction module is configured to extract the movement features of the traffic flow of the side lane;
the second feature extraction module is configured to extract driving features based on a single driving simulator;
an analysis module configured to determine a left and/or right boundary steering angle of a steering wheel corner of a driver without significant steering intent based on the side-lane traffic flow motion characteristics and the driving characteristics.
In a third aspect, embodiments of the present application further provide a driving feature data processing apparatus, including: a memory, a processor, and a user interface;
the memory is used for storing a computer program;
the user interface is used for realizing interaction with a user;
the processor is used for reading the computer program in the memory, and when the processor executes the computer program, the driving characteristic data processing method provided by the invention is realized.
In a fourth aspect, an embodiment of the present application further provides a processor readable storage medium, where a computer program is stored, and when the processor executes the computer program, the driving feature data processing method provided by the present invention is implemented.
According to the driving characteristic data processing method, the side lane traffic flow motion characteristics and the driving characteristics based on the single driving simulator are firstly extracted, then the left boundary steering angle and/or the right boundary steering angle of the steering wheel corner of the driver without obvious steering intention are determined, and a data basis is provided for deviation judgment. The method of the invention extracts unconscious steering behavior and the position distribution rule characteristics of the vehicle in the lane by taking the driver as the center for the data mining of traffic flow movement of the lane beside the high speed and single driving simulator information, provides a data basis for deviation judgment, and can reduce the false alarm rate caused by the unequal situation of vehicle deviation and dangerous situation caused by vehicle deviation.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of driving feature data processing provided in an embodiment of the present invention;
FIG. 2 is a schematic diagram of the relationship among monitoring points, vehicles and lane lines in lane line position estimation;
FIG. 3 is a graph showing the comparison of the fitting results of normal distribution and bias distribution;
fig. 4 is a schematic diagram of extracting driving characteristics based on a single-person driving simulator according to an embodiment of the present application;
fig. 5 is a schematic diagram of a driving feature data processing device according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of another driving feature data processing device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Some words appearing hereinafter are explained:
1. in the embodiment of the invention, the term "and/or" describes the association relation of the association objects, which means that three relations can exist, for example, a and/or B can be expressed as follows: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.
2. The term "plurality" in the embodiments of the present application means two or more, and other adjectives are similar thereto.
The increasing amount of vehicles kept worldwide brings with it the safety problem of the gradual rise of road traffic accidents, and driver distraction is the main cause of traffic accidents. Therefore, intelligent auxiliary driving technology, in particular to a lane keeping auxiliary system which helps a driver to control a vehicle to run in a lane by applying auxiliary torque to a steering wheel, has become one of the key technologies of current intelligent safe driving, and effectively solves the problem that the driver unconsciously drives the vehicle to deviate from a lane line due to factors such as fatigue, distraction, transverse wind and the like. The auxiliary system based on intervention is used as a lane keeping auxiliary technology, a steering wheel torque changing mode is adopted to achieve the purpose of reminding a driver and preventing the driver from deviating further, steering wheel rotation angles are not actively changed, and severe man-machine collision can be effectively avoided.
However, the existing lane keeping assist system mainly focuses on the deviation degree of the vehicle relative to the lane line, and does not consider the driving habit of the driver and the influence of surrounding traffic flow on the danger caused by the deviation of the vehicle, so that the problems of high false alarm rate, excessive intervention degree and the like are caused. And clustering drivers into different types on the whole by adopting a fuzzy clustering algorithm, and respectively carrying out lane departure judgment method design on different driving types. And predicting the future track of the vehicle according to the personal driving data so as to judge whether the vehicle deviates or not, or adopting a reinforcement learning-based method, introducing the input of a driver as an environment variable to estimate the deviation degree of the vehicle so as to calculate the lane keeping auxiliary torque. In the method, although the driving data of the driver is introduced into the decision process, the influence of the driving habit on the lane departure judgment process cannot be established, and the driving characteristics such as unintentional steering behavior of the driver are ignored.
Aiming at the technical problems, the invention provides a driving characteristic data processing method. By mining data of traffic flow movement of a lane beside a high speed and information of a single driving simulator, taking a driver as a center, extracting unconscious driving steering behavior and position distribution rule characteristics of a vehicle in the lane, providing a data basis for deviation judgment, and reducing false alarm rate caused by unequal vehicle deviation conditions and dangerous conditions generated by vehicle deviation.
The following description of the technical solutions in the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
It should be noted that, the display sequence of the embodiments of the present application only represents the sequence of the embodiments, and does not represent the advantages or disadvantages of the technical solutions provided by the embodiments.
Referring to fig. 1, a schematic diagram of a driving feature data processing method provided in an embodiment of the present application, as shown in fig. 1, includes steps S101 to S104:
s101, extracting the traffic flow motion characteristics of a side lane;
in order to measure the degree of risk of vehicle deviation, real-time monitoring of traffic conditions in side lanes is required. In actual running of a vehicle, if a side vehicle is fast-forwarded to a current lane of a main vehicle relative to the speed of the vehicle, a driver of the main vehicle does not make a preparation for avoiding transverse collision in advance due to distraction, and a driving auxiliary system can generate urgent and severe transverse intervention, so that the following problems are caused: 1) The violent shaking of the steering wheel can be caused, so that the sudden change of the position of the steering wheel, namely the sudden steering of the vehicle, is easy to cause the instability of the vehicle in a high-speed scene; 2) Causing the driver to be panicked and creating a poor driving experience. Therefore, the driving assistance system needs to collect traffic flow data in the highway, analyze the traffic flow characteristics of the side lanes, extract the driving position distribution in the side lanes and estimate the lateral danger when the main vehicle deviates so as to avoid the emergency intervention of the system and prevent the occurrence of man-machine collision.
As a preferred example, extracting the side-lane traffic flow movement characteristics may include the following steps A1 to A4:
a1: extracting position information data of a side lane vehicle;
as a preferable example, the position information data of the by-pass vehicle isThe method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>For the lateral position of the geometric center of the vehicle detected by the lidar,/-for>For the longitudinal position of the geometric center of the vehicle detected by the laser radar, i is the data number, i is more than or equal to 1 and less than or equal to n, and n is the total number of data acquired from a real road.
A2: preprocessing the position information data of the side lane vehicle;
as a preferred example, preprocessing the position information data of the by-pass vehicle may include the following A2-1 to A2-3:
a2-1: and converting the coordinate system into data under the coordinate system of the ground where the lane line is located by converting the data under the coordinate system of the sensor acquired by the laser radar.
For example, it is known that during lidar installation, the pitch angle is: -30 °, yaw and roll angles of: 0 deg.. Therefore, the geometric center coordinates of the vehicle under the laser radar can be obtained by the following formula (2.1)Is converted into the ground coordinate systemThe position of the laser radar is the origin under the geodetic coordinate system:
A2-2: estimating the position of the lane line to obtain the distance between the center of the vehicle and the lane line on the left side;
According to the expressway construction standard and specification, designing a lane line position calculating method, and marking the position of a lane line. For example, as shown in FIG. 2, in whichAndrepresenting the vertical distance and the transverse distance from the detection point to the lane line respectively;representing the detection distance from the measuring point to the lane line;representing the detected distance of the measuring point to the adjacent lane line. Assuming that the lane width is d meters, the following formula (2.2) is satisfied:
The distance between the center of the ith vehicle and the lane line on the left side of the ith vehicle can be obtained:
Wherein, is the geometric center coordinate abscissa of the vehicle of the ith vehicle in the geodetic coordinate system.
For the saidAfter square root taking, as shown in fig. 3, the left side diagram 3 (a) in fig. 3 shows a distribution where square root is not taken, and the right side diagram 3 (b) in fig. 3 shows a distribution where square root is taken. As can be seen from fig. 3 (a), the traffic flow is distributed more tightly on the right part of the lane, and the traffic flow is distributed more sparsely on the left part, so that the driving probability of the driver on the right side of the lane is significantly higher than that on the left side. If the vehicle is fitted in the lane with normal distribution, the fitting effect is poor. The vehicle distribution probability assumes a state of steep rise and fall from right to left along the lane, reaching a peak at the right side of the lane center. In the invention, a fitting method of the bias distribution is adopted, firstly, nonlinear transformation is carried out on statistical independent variables (the transverse distance between the geometric center of the vehicle and the lane line on the left side), namely, the transverse coordinatesAnd (5) taking the square root, and fitting the traffic flow distribution data in the lane by using the normal distribution. Comparing the normal distribution fitting of the processed data with the fitting result before processing, and analyzing in fig. 3 (a) and (b) to find that the deviation distribution data after square root processing has a better relation of the position of peak occurrence and the vehicle distribution probability in the lane along with the change of the geometric center of the vehicle and the left lane line relative to the unprocessed normal distribution data.
As a preferred example, in the step A2, A2-0 may be included before A2-1:
a2-0, removing the channel change data.
As a preferred example, the culling of the lane change data may include:
selecting a certain driving direction, marking lane lines Line1, line2, line3, line4 and the like, judging whether the vehicle position is coincident with the lane lines, if so, skipping the detection of the data of the next id, namely eliminating the data; if not, recording the data of the id.
A3: performing normal distribution fitting on position information data of different lanes;
as a preferable example, in order to eliminate the influence of the inter-lane difference on the analysis result, a plurality of lane travel data may be fitted separately, and the average value thereof may be taken as the standard distribution. Wherein the distance between the center of the vehicle and the lane line on the right sideMean of (2)Sum of variancesCalculated by the following formulas (2.4.1) and (2.4.2):
For example, the distance of the center of a 6-lane vehicle from the right lane lineThe square root obtained distribution is shown in table 1 below.
A4: and determining the traffic flow motion characteristics of the side lanes according to the normal distribution fitting.
As a preferred example, the side-lane traffic flow movement characteristics include one or a combination of the following:
distributing probabilities in lanes by the geometric center of the vehicle;
the probability of the vehicle being distributed on the right lane line;
the probability of the distribution of the vehicle on the left lane line;
the distribution probability of the vehicles in the deviated distance when the vehicles deviate leftwards;
the probability of vehicle distribution within the offset distance when the vehicle is offset to the right.
As a preferred example, the above-mentioned side-lane traffic-flow movement characteristics are respectively determined by the following formulas:
the vehicle geometric center distributes probabilities in a lane as follows:
The distribution probability of the lane lines on the right side of the vehicle is as follows:
The distribution probability of the lane lines on the left side of the vehicle is that
When the vehicle deviates leftwards, the distribution probability of the vehicle in the deviation distance is as follows:
The vehicle distribution probability in the deviated distance when the vehicle deviates rightward is as follows:
Wherein s is the transverse distance between the geometric center of the vehicle and the left/right lane line, and comprisesAnd,for the distance between the center of the vehicle and the lane line on the right side,is thatIs used for the average value of (a),is thatIs a function of the variance of (a),d is the lane width, and N () is the probability density function normal distribution sign, which is the distance between the center of the vehicle and the lane line on the left side.
S102, extracting driving characteristics based on a single driving simulator;
in order to reduce the excessive interference influence on the normal driving of the driver and prevent the driver from being panicked, the key of designing a personalized system conforming to the driving habit is to extract the driving habit characteristics of the driver, and the key is mainly reflected in the control input of the driver and the movement state of the vehicle.
To keep the vehicle in the middle of the lane, the driver often needs to constantly adjust the steering wheel angle. The reason for this is: 1) Under a real road environment, a plurality of environmental factors can exert force on a vehicle to influence the running track of the vehicle, for example, the road surface is often uneven due to the pits and the bulges, so that the stress of the tire is deformed and displaced by a small angle, and the real track of the vehicle and the theoretical track are offset to different degrees; 2) The dynamic characteristics of the vehicle can influence the motion track, for example, the centrifugal force can cause the vehicle to turn understeer when the vehicle passes through a curve, and the vehicle can sideslip when the vehicle runs on a road surface with a lateral gradient under the influence of gravity component force, so that the running track is changed. Therefore, when the driver operates the vehicle to drive in the lane, the direction of the vehicle head is often continuously adjusted, but the vehicle cannot be always driven in the center of the lane. When the degree of deviation of the vehicle from the center line of the lane is the same, in order to keep the vehicle running at the position expected by the driver, the maintenance measures taken by different drivers are different, for example, a conservative driver is often sensitive to the deviation condition of the vehicle, and when the vehicle is found to deviate to a small extent, the steering wheel is operated to correct the direction of the vehicle head, so that the steering wheel driving operation with a high frequency and a small angle is presented; the aggressive driver is opposite, when the vehicle deviates to a large extent, the steering operation with a large angle is adopted to correct the direction of the vehicle head, and the characteristic of low frequency and large angle is presented.
In addition, since the driver is located at the left part in the vehicle, it is not possible to well determine whether the distances between the vehicle and the two lane lines are equal, and a relatively fixed deviation is generated between the running distribution center in the lane and the lane center according to the observation habit of the driver. It is therefore necessary to collect data of the driving distribution of the vehicle in the lane for statistical regularity.
As a preferred example, in the embodiment of the invention, the distance between the center of the vehicle and the left lane is selected asAs a representation of the lateral position of the vehicle within the lane, by counting the probability distribution of the driving position preference of the driver, the driving characteristics based on the single-person driving simulator are extracted, as shown in fig. 4, including steps S301 to S303:
s301, performing off-state distribution fitting on the transverse position of the vehicle to obtain distribution
In this step, when the independent variable is processed by the cubic method, the bias distribution fitting is performed, the peak value of the result is relatively close to the statistical peak value of the data, and the distribution is more symmetric left and right, and the step can be expressed as:
Wherein the method comprises the steps ofFor the distance between the center of the vehicle and the left lane line,to fit the driver's preferred lateral position when controlling the vehicle to travel within the lane,to fit the vehicle lateral position variance.To fit the steering angle distribution center when the driver is unintentionally steering,the variance of steering wheel angle distribution at the time of the unintentional steering is fitted.
Preferably, this step can also be divided into the following steps:
performing a third-order process on the lateral position of the vehicle;
and (5) performing normal distribution fitting.
S302, deleting data of the vehicle deviated from the driver preference driving position;
in order to reduce the influence of the driver on the overall data analysis result caused by the error driving behavior, the method for removing the data corresponding to the small probability event is adopted to analyze the relation between the lateral deviation of the relative driving preference position of the vehicle and the steering wheel angle. The low probability event refers to an event with occurrence probability smaller than a preset threshold (the preset threshold is preset according to needs, for example, 5%). Correspondingly, the horizontal axis intervalThe inner area is larger than the preset thresholdThe piece is for example 95.45%. Therefore, the invention eliminates the small probability event data outside the (-2σ,2σ) interval according to the fitting result.
S303, steering wheel turning angle in the processed data setNormal distribution fitting is carried out to obtain the distribution characteristics of the steering angle of the vehicle when the driver unconsciously steers;
Specifically, S303 may include: and carrying out normal distribution fitting on all steering wheel rotation angle data in the data after deleting the data of the vehicle which deviates from the driving position preferred by the driver.
S103, determining the left boundary steering angle and/or the right boundary steering angle of the steering wheel corner of the driver without obvious steering intention according to the side lane traffic flow motion characteristics and the driving characteristics.
When the driver drives the vehicle and no obvious steering intention is made, the steering wheel angle always remains within a certain interval, and the interval is relatively stable in size when the vehicle speed changes. When the distance between the vehicle and the preferential running center is gradually increased, the section where the steering wheel angle is positioned is also gradually enlarged, and when the deviation distance is larger, the driver can increase the steering wheel angle input due to the purpose of correcting the transverse position of the vehicle.
In the present invention, first, the lateral offset of the vehicle with respect to the driving preference position is calculatedAngle with steering wheelCorrelation coefficient between the two.
The average value of the lateral offset r of the vehicle relative to the driving preference position is as follows:
Wherein, m is the number of data pieces collected from the driving simulator, r i And i is a data number, i is greater than or equal to 1 and less than or equal to m, for the ith lateral offset data.
It should be noted that the lateral offset r of the vehicle relative to the driving preference position is the lateral position of the vehicle acquired from the driving simulator and the fitted driving preference position of the driverOffset between them.
The average value of the direction angle SW is:
SW i Is the i-th direction angle data.
The variance of the vehicle relative to the driving preference position lateral offset r is:
The variance of the direction angle SW is:
The covariance of r and SW is:
The correlation coefficients of r and SW are therefore:
For example, if the correlation coefficientEqual to 0.449, the steering wheel position and the vehicle travel are describedThere is a moderate correlation of locations.
When the vehicle is more off-center, the driver can consciously apply the steering wheel angle to correct the vehicle. But it is difficult to embody unintentional driving behavior of the driver during lane keeping. Further, the invention selects the data of the vehicle in the preference center to perform normal distribution fitting, namely when the vehicle transversely deviates from the driving preference positionWhen the driver considers that the vehicle is traveling at the desired position. Select to satisfyAnd (3) carrying out normal distribution fitting on the data of the steering wheel, so that the steering wheel angle distribution condition of the driver in the free driving state can be obtained. Preferably, the invention can obtain steering wheel corner left/right boundary steering of a driver without obvious steering intention, namely:
the left boundary steering angle of the steering wheel angle of the driver without obvious steering intention is as follows:
The right boundary steering angle of the steering wheel angle of the driver without obvious steering intention is:
Wherein the method comprises the steps ofTo fit the steering angle distribution center when the driver is unintentionally steering,to fit the steering wheel angle distribution variance at unintended steering, SW is the vehicle steering wheel angle.
The lateral driving position is a driver driving preference position, and the steering angle is a free steering boundary angle to the left or right of the driver.
According to the method, the side lane traffic flow movement characteristics and the driving characteristics based on the single driving simulator are extracted, and then the left boundary steering angle and/or the right boundary steering angle of the steering wheel corner of the driver without obvious steering intention are determined according to the side lane traffic flow movement characteristics and the driving characteristics, so that the false alarm rate caused by unequal vehicle deviation conditions and dangerous conditions generated by vehicle deviation is reduced.
Based on the same inventive concept, the embodiment of the invention also provides a driving characteristic data processing device, as shown in fig. 5, the apparatus includes:
a first feature extraction module 401 configured to extract a side-lane traffic flow motion feature;
a second feature extraction module 402 configured to extract driving features based on a single-person driving simulator;
an analysis module 403 configured to determine a left and/or right boundary steering angle of a steering wheel corner of the driver without significant steering intent based on the side-lane traffic flow movement characteristics and the driving characteristics.
As a preferred example, the feature extraction module one 401 is configured to extract the side-lane traffic flow movement feature by:
extracting position information data of a side lane vehicle;
preprocessing the position information data of the side lane vehicle;
performing normal distribution fitting on position information data of different lanes;
and determining the traffic flow motion characteristics of the side lanes according to the normal distribution fitting.
Wherein, for the lateral position of the geometric center of the vehicle detected by the lidar,/-for>The longitudinal position i of the geometric center of the vehicle detected by the laser radar is a data number, i is more than or equal to 1 and less than or equal to n, and n is the total number of data acquired from a real road.
As a preferred example, the feature extraction module one 401 is configured to pre-process the position information data of the side-lane vehicle:
converting a coordinate system, namely converting data under a sensor coordinate system acquired by a laser radar into data under a geodetic coordinate system where a lane line is located;
estimating the position of the lane line to obtain the distance between the center of the vehicle and the lane line on the left side;
The said movement characteristics according to the said side traffic flow include one or a combination of the following:
distributing probabilities in lanes by the geometric center of the vehicle;
the probability of the vehicle being distributed on the right lane line;
the probability of the distribution of the vehicle on the left lane line;
the distribution probability of the vehicles in the deviated distance when the vehicles deviate leftwards;
the probability of vehicle distribution within the offset distance when the vehicle is offset to the right.
Wherein the probability of the distribution of the geometric center of the vehicle in the lane is that;
When the vehicle deviates leftwards, the distribution probability of the vehicle in the deviation distance is as follows:
the vehicle distribution probability in the deviated distance when the vehicle deviates rightward is as follows:
wherein s is the transverse distance between the geometric center of the vehicle and the left/right lane line, and comprisesAnd,for the distance between the center of the vehicle and the lane line on the right side,is thatIs used for the average value of (a),is thatIs a function of the variance of (a),d is the lane width, and N () is the probability density function normal distribution sign, which is the distance between the center of the vehicle and the lane line on the left side.
As a preferred example, the feature extraction module two 402 is further configured to extract driving features based on a single-person driving simulator according to the following manner:
removing the channel changing data;
performing off-state distribution fitting on the transverse position of the vehicle to obtain distribution;
Deleting data of the vehicle deviating from the driver's preferred driving position;
steering wheel angle in processed data setNormal distribution fitting is carried out to obtain the distribution characteristics of the steering angle of the vehicle;
Wherein the method comprises the steps ofFor the distance between the center of the vehicle and the left lane line,to fit the driver's preferred lateral position when controlling the vehicle to travel within the lane,to fit the vehicle lateral position variance.To fit the steering angle distribution center when the driver is unintentionally steering,the variance of steering wheel angle distribution at the time of the unintentional steering is fitted.
Preferably, the second feature extraction module 402 is further configured to perform a bias distribution fitting on the lateral position of the vehicle to obtain a distribution:
performing a third-order process on the lateral position of the vehicle;
and (5) performing normal distribution fitting.
The deleting the data of the vehicle deviating from the driver's preferred driving position includes:
The normal distribution fitting of steering wheel angles in the processed data set to obtain the vehicle steering angle distribution characteristics comprises the following steps:
and carrying out normal distribution fitting on all steering wheel rotation angle data in the data after deleting the data of the vehicle which deviates from the driving position preferred by the driver.
As a preferred example, the analysis module 403 is configured to determine a left boundary steering angle of the steering wheel angle for the driver without significant steering intent:
as a preferred example, the analysis module 403 is configured to determine a right boundary steering angle of the steering wheel angle for the driver without significant steering intent:
wherein the method comprises the steps ofTo fit the steering angle distribution center when the driver is unintentionally steering,to fit the steering wheel angle distribution variance at unintended steering, SW is the vehicle steering wheel angle.
It should be noted that, the feature extraction module one 401 provided in this embodiment can implement all functions included in S101, solve the same technical problem, achieve the same technical effect, and are not described herein again;
it should be noted that, the feature extraction module two 402 provided in this embodiment can implement all functions included in S102, solve the same technical problem, and achieve the same technical effect, which is not described herein again;
it should be noted that, the analysis module 403 provided in this embodiment can implement all functions included in S103, solve the same technical problem, and achieve the same technical effect, which is not described herein again;
it should be noted that the device and the method belong to the same inventive concept, solve the same technical problem, achieve the same technical effect, and are not described in detail.
Based on the same inventive concept, the embodiment of the invention also provides a driving characteristic data processing device, as shown in fig. 6, which comprises:
including a memory 502, a processor 501, and a user interface 503;
the memory 502 is used for storing a computer program;
the user interface 503 is configured to interact with a user;
the processor 501 is configured to read a computer program in the memory 502, where the processor 501 implements:
extracting the traffic flow motion characteristics of the side lanes;
extracting driving characteristics based on a single driving simulator;
and determining the left boundary steering angle and/or the right boundary steering angle of the steering wheel corner of the driver without obvious steering intention according to the side lane traffic flow motion characteristics and the driving characteristics.
Wherein in fig. 5, a bus architecture may comprise any number of interconnected buses and bridges, and in particular one or more processors represented by processor 501 and various circuits of memory represented by memory 502, linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., which are well known in the art and, therefore, will not be described further herein. The bus interface provides an interface. The processor 501 is responsible for managing the bus architecture and general processing, and the memory 502 may store data used by the processor 501 in performing operations.
The processor 501 may be CPU, ASIC, FPGA or CPLD, and the processor 501 may also employ a multi-core architecture.
When the processor 501 executes the computer program stored in the memory 502, any driving characteristic data processing method in the first embodiment is implemented.
It should be noted that, the device and the method belong to the same inventive concept, solve the same technical problem, achieve the same technical effect, and the same points are not repeated.
The present application also proposes a processor readable storage medium. The processor-readable storage medium stores a computer program, and the processor implements any driving feature data processing method in the first embodiment when executing the computer program.
It should be noted that, in the embodiment of the present application, the division of the units is schematic, which is merely a logic function division, and other division manners may be implemented in actual practice. In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (11)
1. A driving characteristic data processing method, characterized by comprising:
extracting the traffic flow motion characteristics of the side lanes;
extracting driving characteristics based on a single driving simulator;
determining a left boundary steering angle and/or a right boundary steering angle of a steering wheel corner of a driver without obvious steering intention according to the side lane traffic flow motion characteristics and the driving characteristics;
the extracting the side lane traffic flow movement characteristics comprises the following steps:
extracting position information data of a side lane vehicle;
preprocessing the position information data of the side lane vehicle;
performing normal distribution fitting on position information data of different lanes;
determining the traffic flow motion characteristics of the side lanes according to the normal distribution fitting;
the side-lane traffic flow movement characteristics include one or a combination of the following:
distributing probabilities in lanes by the geometric center of the vehicle;
the probability of the vehicle being distributed on the right lane line;
the probability of the distribution of the vehicle on the left lane line;
the distribution probability of the vehicles in the deviated distance when the vehicles deviate leftwards;
the probability of vehicle distribution in the deviated distance when the vehicle deviates rightward;
the extracting driving characteristics based on the single-person driving simulator comprises the following steps:
performing off-state distribution fitting on the transverse position of the vehicle to obtain distribution;
Deleting data of the vehicle deviating from the driver's preferred driving position;
steering wheel angle in processed data setNormal distribution fitting is carried out to obtain the distribution characteristics of the steering angle of the vehicle;
Wherein the method comprises the steps ofFor the distance between the centre of the vehicle and the lane line on the left side, < >>For fitted drivingThe driver controls the preferred lateral position of the vehicle when driving in the lane,/->For the fitted vehicle lateral position variance +.>For the fitted steering angle distribution center when the driver is unconsciously steering, +.>To fit the steering wheel angle distribution variance at the unintentional steering, N () is the probability density function normal distribution sign.
2. The method of claim 1, wherein the position information data of the side-track vehicle includes:
Wherein, for the lateral position of the geometric center of the vehicle detected by the lidar,/-for>For the longitudinal position of the geometric center of the vehicle detected by the laser radar, i is the data number, i is more than or equal to 1 and less than or equal to n, and n is the total number of data acquired from a real road.
3. The method of claim 1, wherein the preprocessing the position information data of the side-track vehicle comprises:
converting a coordinate system, namely converting data under a sensor coordinate system acquired by a laser radar into data under a geodetic coordinate system where a lane line is located;
estimating the position of the lane line to obtain the distance between the center of the vehicle and the lane line on the left side;
4. The method according to claim 1, characterized in that it comprises:
When the vehicle deviates leftwards, the distribution probability of the vehicle in the deviation distance is as follows:
the vehicle distribution probability in the deviated distance when the vehicle deviates rightward is as follows:
wherein s is the transverse distance between the geometric center of the vehicle and the left/right lane line, and comprisesAnd->,/>For the distance between the centre of the vehicle and the lane line on the right side,/-for the distance between the centre of the vehicle and the lane line on the right side>For->Mean value of->For->Variance (L)/(L)>D is the lane width, and N () is the probability density function normal distribution sign, which is the distance between the center of the vehicle and the lane line on the left side.
7. The method of claim 6, wherein the performing a normal distribution fit to the steering wheel angle in the processed dataset to obtain a vehicle steering angle distribution feature comprises:
8. The method of claim 1, wherein determining a left and/or right boundary steering angle of a steering wheel corner of the driver without significant steering intent based on the side-lane traffic flow characteristics and the driving characteristics comprises:
the left boundary steering angle of the steering wheel angle of the driver without obvious steering intention is as follows:
the right boundary steering angle of the steering wheel angle of the driver without obvious steering intention is:
9. A driving characteristic data processing apparatus, characterized by comprising:
the first feature extraction module is configured to extract the movement features of the traffic flow of the side lane;
the second feature extraction module is configured to extract driving features based on a single driving simulator;
an analysis module configured to determine a left and/or right boundary steering angle of a steering wheel corner of a driver without significant steering intent based on the side-lane traffic flow motion feature and the driving feature;
the extracting the side lane traffic flow movement characteristics comprises the following steps:
extracting position information data of a side lane vehicle;
preprocessing the position information data of the side lane vehicle;
performing normal distribution fitting on position information data of different lanes;
determining the traffic flow motion characteristics of the side lanes according to the normal distribution fitting;
the side-lane traffic flow movement characteristics include one or a combination of the following:
distributing probabilities in lanes by the geometric center of the vehicle;
the probability of the vehicle being distributed on the right lane line;
the probability of the distribution of the vehicle on the left lane line;
the distribution probability of the vehicles in the deviated distance when the vehicles deviate leftwards;
the probability of vehicle distribution in the deviated distance when the vehicle deviates rightward;
the extracting driving characteristics based on the single-person driving simulator comprises the following steps:
performing off-state distribution fitting on the transverse position of the vehicle to obtain distribution;
Deleting data of the vehicle deviating from the driver's preferred driving position;
steering wheel angle in processed data setNormal distribution fitting is carried out to obtain the distribution characteristics of the steering angle of the vehicle;
Wherein the method comprises the steps ofFor the distance between the centre of the vehicle and the lane line on the left side, < >>Controlling a preferred lateral position of the vehicle while driving in the lane for the fitted driver, +.>For the fitted vehicle lateral position variance +.>For the fitted steering angle distribution center when the driver is unconsciously steering, +.>To fit the steering wheel angle distribution variance at the unintentional steering, N () is the probability density function normal distribution sign.
10. A driving characteristics data processing device, characterized by comprising a memory, a processor and a user interface;
the memory is used for storing a computer program;
the user interface is used for realizing interaction with a user;
the processor being configured to read a computer program in the memory, the processor implementing the driving characteristic data processing method according to one of claims 1 to 8 when the computer program is executed.
11. A processor-readable storage medium, characterized in that the processor-readable storage medium stores a computer program, which when executed by the processor implements the driving characteristic data processing method according to one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310241023.0A CN115946710B (en) | 2023-03-14 | 2023-03-14 | Driving characteristic data processing method, device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310241023.0A CN115946710B (en) | 2023-03-14 | 2023-03-14 | Driving characteristic data processing method, device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115946710A CN115946710A (en) | 2023-04-11 |
CN115946710B true CN115946710B (en) | 2023-06-16 |
Family
ID=85906993
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310241023.0A Active CN115946710B (en) | 2023-03-14 | 2023-03-14 | Driving characteristic data processing method, device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115946710B (en) |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004322787A (en) * | 2003-04-23 | 2004-11-18 | Nissan Motor Co Ltd | Lane departure prevention device |
ITMI20050788A1 (en) * | 2005-05-02 | 2006-11-03 | Iveco Spa | RIDING AID SYSTEM TO SUPPORT THE CORSA MAINTENANCE TO ASSIST THE CHANGE OF SLIDES AND MONITOR THE STATE OF THE DRIVER OF A VEHICLE |
DE102011018159A1 (en) * | 2011-04-19 | 2012-10-25 | GM Global Technology Operations LLC (n. d. Gesetzen des Staates Delaware) | Device and method for driver assistance |
CN102336163B (en) * | 2011-08-31 | 2014-06-25 | 同济大学 | Vehicle yaw detection device |
CN107031623B (en) * | 2017-03-16 | 2019-09-20 | 浙江零跑科技有限公司 | A kind of road method for early warning based on vehicle-mounted blind area camera |
US10668925B2 (en) * | 2017-09-05 | 2020-06-02 | Baidu Usa Llc | Driver intention-based lane assistant system for autonomous driving vehicles |
US11654936B2 (en) * | 2018-02-05 | 2023-05-23 | Sony Corporation | Movement device for control of a vehicle based on driver information and environmental information |
CN108438004A (en) * | 2018-03-05 | 2018-08-24 | 长安大学 | Lane departure warning system based on monocular vision |
CN114379553B (en) * | 2021-12-23 | 2023-12-08 | 浙江吉利控股集团有限公司 | Driving support control method, driving support control device, and driving support system |
-
2023
- 2023-03-14 CN CN202310241023.0A patent/CN115946710B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN115946710A (en) | 2023-04-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3647728B1 (en) | Map information system | |
US9077958B2 (en) | Road departure warning system | |
EP2949548B1 (en) | Lane keeping suppressing system and method | |
CN113071505B (en) | Method, device and equipment for determining driving behavior habit and controlling vehicle running | |
WO2018036892A1 (en) | Driving assistance method and system for vehicle | |
CN112249008B (en) | Unmanned automobile early warning method aiming at complex dynamic environment | |
EP3666612A1 (en) | Vehicle control device | |
CN114265411B (en) | Method for solving problem that performance of vehicle prediction model is limited by perceived data performance | |
CN113119960B (en) | System and method for providing vehicle safety distance and speed warning under road-slip condition | |
CN112937608B (en) | Track prediction-based integrated rolling decision method and device for unmanned vehicle in ice and snow environment and storage medium | |
Tomar et al. | Safety of Lane Change Maneuver Through A Priori Prediction of Trajectory Using Neural Networks. | |
Cerni et al. | Naturalistic driving data collection to investigate into the effects of road geometrics on track behaviour | |
US11390292B2 (en) | Method for proposing a driving speed | |
CN115946710B (en) | Driving characteristic data processing method, device and storage medium | |
Johnson et al. | Investigation of driver lane keeping behavior in normal driving based on naturalistic driving study data | |
CN111104824A (en) | Method for detecting lane departure, electronic device, and computer-readable storage medium | |
Lattke et al. | Road departure protection-a means for increasing driving safety beyond road limits | |
Orfila et al. | Modeling of dynamic vehicle–road interactions for safety-related road evaluation | |
Freeman et al. | Run-off-road and recovery–state estimation and vehicle control strategies | |
CN114882706B (en) | Circumferential anti-collision early warning method and system based on unstructured road surface | |
Xu et al. | A new lane departure warning algorithm considering the driver’s behavior characteristics | |
EP3810471A1 (en) | System and method to navigate autonomous vehicles | |
CN116071714A (en) | Lane departure detection method, system, electronic device, and readable storage medium | |
Levison | Interactive highway safety design model: Issues related to driver modeling | |
CN111338341B (en) | Vehicle obstacle avoidance method and device, electronic device, vehicle and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |