CN109878530B - Method and system for identifying lateral driving condition of vehicle - Google Patents
Method and system for identifying lateral driving condition of vehicle Download PDFInfo
- Publication number
- CN109878530B CN109878530B CN201910152307.6A CN201910152307A CN109878530B CN 109878530 B CN109878530 B CN 109878530B CN 201910152307 A CN201910152307 A CN 201910152307A CN 109878530 B CN109878530 B CN 109878530B
- Authority
- CN
- China
- Prior art keywords
- preset
- driving condition
- time
- vehicle
- condition
- 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
- 238000000034 method Methods 0.000 title claims abstract description 145
- 230000008569 process Effects 0.000 claims abstract description 106
- 230000008859 change Effects 0.000 claims abstract description 53
- 238000006073 displacement reaction Methods 0.000 claims abstract description 39
- 238000004364 calculation method Methods 0.000 claims description 58
- 238000005070 sampling Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 5
- 208000003443 Unconsciousness Diseases 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
Abstract
The invention provides a method for identifying the lateral driving condition of a vehicle, which comprises the following steps: identifying a vehicle steering process; calculating the identified working condition identification data in the steering process, wherein the working condition identification data comprises a course angle change angle, a weighted distance sum between a course angle process curve and a preset typical lane changing template curve, a maximum yaw rate and lateral displacement; the weighted distance sum is obtained based on a dynamic warping algorithm; and determining the running conditions of the steering process based on the calculated condition identification data, wherein the running conditions comprise turning running conditions, turning running conditions and lane changing running conditions. The invention also provides a system for identifying the lateral running condition of the vehicle. The method integrates the dynamic time warping algorithm to identify the lane-changing driving condition in the lateral driving condition of the vehicle, so that the identification method has good adaptability and high identification accuracy, and the lane-changing condition precision rate reaches over 90 percent, thereby more accurately determining the operation condition of the driver on the vehicle.
Description
Technical Field
The invention relates to a method and a system for identifying a vehicle running condition, in particular to a method and a system for identifying a vehicle lateral running condition.
Background
Vehicle driving condition recognition is an important basic work for driving style recognition and driving behavior analysis. By identifying the driving condition of the vehicle, the process of operating the vehicle by the driver can be determined, and then the driving behavior and the driving style are analyzed.
In the past vehicle driving condition recognition, there are methods of recognizing the vehicle driving condition based on the lane line mark and the position change of the vehicle relative to the lane line by using the traffic environment signal obtained by the vehicle-mounted intelligent camera, and there are also methods of recognizing by using the vehicle state signal in the vehicle chassis CAN communication network. However, the current intelligent camera is low in vehicle assembly rate and cannot be widely used, and in addition, the current traditional method for identifying the lateral driving working condition by using the chassis CAN signal is low in precision and difficult to meet the requirements of driving style and driving behaviors.
Disclosure of Invention
In view of the above, the present invention aims to provide a method and a system for identifying a lateral driving condition of a vehicle, which have high identification accuracy and can meet the requirements of driving style and driving behavior.
The technical scheme adopted by the invention is as follows:
the embodiment of the invention provides a method for identifying a lateral driving condition of a vehicle, which comprises the following steps:
recognizing the steering process of the vehicle by using a preset steering recognition method;
calculating the identified working condition identification data in the steering process, wherein the working condition identification data comprises a course angle change angle, a weighted distance sum between a course angle process curve and a preset typical lane changing template curve, a maximum yaw velocity and lateral displacement; the weighted distance sum is obtained based on a dynamic warping algorithm;
and determining the driving condition to which the steering process belongs based on the calculated condition identification data, wherein the driving condition comprises a turning driving condition, a turning driving condition and a lane changing driving condition, the turning driving condition and the turning driving condition are identified based on the course angle change angle, and the lane changing driving condition is identified based on the weighted distance sum, the maximum yaw rate and the lateral displacement.
Optionally, the recognizing the vehicle steering process by using a preset steering recognition method includes:
calculating the short-time average energy of the yaw velocity in the preset time at the first calculation moment;
recording the first calculation time as the starting time of the vehicle steering process when the average energy of the calculated yaw rate at the first calculation time is larger than a first set threshold value when the short-term average energy of the calculated yaw rate at the first calculation time is larger than the first set threshold value;
at the second calculation moment, calculating the short-time average energy of the yaw velocity in the preset time;
when the average energy of the short-term yaw rate calculated at the second calculation moment is smaller than a second set threshold value, recording the second calculation moment as the end time of the vehicle steering process;
the first set threshold is greater than the second set threshold.
Optionally, the preset time is 2 s; said first set threshold being 0.5(°/s)2(ii) a Said second set threshold being 0.25(°/s)2。
Optionally, the determining, based on the calculated operating condition identification data, a driving operating condition to which the steering process belongs specifically includes:
when the calculated course angle change angle is located in a first change interval, judging that the steering process belongs to a turning running working condition;
when the calculated course angle change angle is located in a second change interval, judging that the steering process belongs to a U-turn driving working condition;
when the weighted distance sum is smaller than a preset weighted distance threshold value, the maximum value of the yaw velocity is smaller than a preset yaw velocity threshold value, and the lateral displacement is within a preset displacement range, judging that the steering process belongs to a lane-changing driving working condition;
the first variation interval is smaller than the second variation interval.
Optionally, the first variation interval is [75 °, 105 ° ];
the second variation interval is [150 degrees, 210 degrees ];
the preset weighted distance threshold is 0.1;
the preset yaw velocity threshold value is 10 degrees/s; the preset displacement range is [1.5m, 6.5m ].
Another embodiment of the present invention provides a system for identifying a lateral driving condition of a vehicle, including:
the steering identification module is used for identifying the steering process of the vehicle by using a preset steering identification method;
the operating condition identification data calculation module is used for calculating the identified operating condition identification data in the steering process, and the operating condition identification data comprises a course angle change angle, the sum of weighted distances between a course angle process curve and a preset typical lane change template curve, the maximum value of a yaw angular velocity and lateral displacement; the weighted distance sum is obtained based on a dynamic warping algorithm;
and the driving condition identification module is used for determining the driving condition to which the steering process belongs based on the calculated working condition identification data, wherein the driving condition comprises a turning driving condition, a turning driving condition and a lane changing driving condition, the turning driving condition and the turning driving condition are identified based on the course angle change angle, and the lane changing driving condition is identified based on the weighted distance sum, the maximum yaw angular velocity and the lateral displacement.
Optionally, the steering identification module specifically identifies a steering process of the vehicle by:
calculating the short-time average energy of the yaw velocity in the preset time at the first calculation moment;
recording the first calculation time as the starting time of the vehicle steering process when the average energy of the calculated yaw rate at the first calculation time is larger than a first set threshold value when the short-term average energy of the calculated yaw rate at the first calculation time is larger than the first set threshold value;
at the second calculation moment, calculating the short-time average energy of the yaw velocity in the preset time;
when the average energy of the short-term yaw rate calculated at the second calculation moment is smaller than a second set threshold value, recording the second calculation moment as the end time of the vehicle steering process;
the first set threshold is greater than the second set threshold.
Optionally, the preset time is 2 s; said first set threshold being 0.5(°/s)2(ii) a Said second set threshold being 0.25(°/s)2。
Optionally, the driving condition identification module is specifically configured to:
when the calculated course angle change angle is located in a first change interval, judging that the steering process belongs to a turning running working condition;
when the calculated course angle change angle is located in a second change interval, judging that the steering process belongs to a U-turn driving working condition;
when the weighted distance sum is smaller than a preset weighted distance threshold value, the maximum value of the yaw velocity is smaller than a preset yaw velocity threshold value, and the lateral displacement is within a preset displacement range, judging that the steering process belongs to a lane-changing driving working condition;
the first variation interval is smaller than the second variation interval.
Optionally, the first variation interval is [75 °, 105 ° ]; the second variation interval is [150 degrees, 210 degrees ]; the preset weighted distance threshold is 0.1; the preset yaw velocity threshold value is 10 degrees/s; the preset displacement range is [1.5m, 6.5m ].
The method and the system for identifying the lateral driving condition of the vehicle provided by the embodiment of the invention firstly identify the steering process, identify the turning and turning-around driving conditions based on the course angle change angle when an effective steering process is identified, and identify the lane-changing driving condition in the steering process based on the weighted distance sum between the course angle course curve and the preset typical lane-changing template curve, the maximum yaw angle speed and the lateral displacement, so that the identification method has good adaptability and high identification accuracy because the dynamic time warping algorithm is fused to identify the lane-changing driving condition in the lateral driving condition of the vehicle, and the precision rate of the lane-changing working condition reaches more than 90 percent, thereby being capable of more accurately determining the operation condition of a driver on the vehicle.
Drawings
FIG. 1 is a schematic flow chart illustrating a method for identifying a lateral driving condition of a vehicle according to an embodiment of the present invention;
FIG. 2 is a detailed flow chart of the steering process identification;
fig. 3 is a block diagram of a system for identifying a lateral driving condition of a vehicle according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments.
FIG. 1 is a flowchart illustrating a method for identifying a lateral driving condition of a vehicle according to an embodiment of the present invention. As shown in FIG. 1, the method for identifying the lateral driving condition of the vehicle provided by the embodiment of the invention can comprise the following steps:
s100, recognizing the steering process of the vehicle by using a preset steering recognition method;
s110, working condition identification data in the identified steering process are calculated, wherein the working condition identification data comprise course angle change angles, the sum of weighted distances between course angle process curves and preset typical lane changing template curves, the maximum value of yaw angular velocity and lateral displacement; the weighted distance sum is obtained based on a dynamic warping algorithm;
and S120, determining the driving condition to which the steering process belongs based on the calculated condition identification data, wherein the driving condition comprises a turning driving condition, a turning driving condition and a lane changing driving condition, the turning driving condition and the turning driving condition are identified based on the course angle change angle, and the lane changing driving condition is identified based on the weighted distance sum, the maximum yaw rate and the lateral displacement.
In the following, the steering process recognition will be first described with reference to fig. 2.
In the embodiment of the invention, the identification of the vehicle steering process by using the preset steering identification method comprises the following steps:
calculating the short-time average energy of the yaw velocity in the preset time at the first calculation moment;
recording the first calculation time as the starting time of the vehicle steering process when the average energy of the calculated yaw rate at the first calculation time is larger than a first set threshold value when the short-term average energy of the calculated yaw rate at the first calculation time is larger than the first set threshold value;
at the second calculation moment, calculating the short-time average energy of the yaw velocity in the preset time;
when the average energy of the short-term yaw rate calculated at the second calculation moment is smaller than a second set threshold value, recording the second calculation moment as the end time of the vehicle steering process;
the first set threshold is greater than the second set threshold.
The above-described recognition method may be performed by a controller having an arithmetic control function. The controller can carry out operation in a fixed calculation period, namely, corresponding operation and control operation are carried out at each calculation time, and the interval between two adjacent calculation times is one calculation period. The first calculation time is a calculation time before the identification start time, and the second calculation time is a calculation time after the steering process start time is determined.
The steering process can be regarded as the whole process that the vehicle is in a straight line stable driving state and is subjected to the steering process and returns to the straight line stable driving state. The yaw rate short-term average energy calculation can be determined by the following equation (1):
wherein E is the short-term average energy in units of (°/s)2And omega is a yaw angular velocity, which is obtained by a sensor, and has the unit of DEG/s, k is an average energy duration range, k is T/dt, dt is a time interval for sampling the yaw angular velocity, and T is a preset time for calculating the short-term average energy of the yaw angular velocity.
A small, unintentional steering maneuver during the maneuver by the driver is characterized by a shorter duration or a smaller peak yaw rate during the maneuver. By selecting a proper calculation time range T, the amplitude of the short-time average energy E of the yaw angular velocity can be calculated to effectively distinguish tiny and unconscious steering operation from normal steering operation.
Further, the first set threshold and the second set threshold for steering process recognition may be determined based on signal quality during actual recognition, and in one example, the first set threshold may be 0.5(°/s)2The second set threshold may be 0.25(°/s)2。
In one embodiment, the steering process identification of an embodiment of the present invention may be as shown in FIG. 2. As shown in fig. 2, at the beginning of each steering process identification, the identification can be performed by the following steps:
s101, judging whether the steering process flag bit is a first set flag value or not; if the first set flag value is the first set flag value, go to step S102; the first set flag value is indicative that the vehicle is not in a steering process; otherwise, the process proceeds to step S104.
In this step, the first setting flag value may be represented by 0, and the steering process flag is defaulted to the first setting flag value at the start of the identification.
S102, calculating the short-time average energy of the yaw rate within the preset time, and judging whether the calculated short-time average energy of the yaw rate is larger than a first set threshold value or not; if yes, go to step S103; otherwise, return to step S101.
S103, updating the flag bit of the current steering process into a second set flag value different from the first set flag value, and recording the starting time of the steering process; the second set flag value represents that the vehicle is in a steering process; the process returns to step S101.
In this step, the second set flag value may be represented by 1.
S104, calculating short-time average energy of the yaw rate within preset time, and judging whether the short-time average energy of the yaw rate is smaller than a second set threshold value or not; if yes, go to step S105; otherwise, returning to step S101, the steering process of the vehicle can be effectively recognized through the above-described steps S101 to S105.
During the straight-line driving process of a driver driving a vehicle, the steering wheel is adjusted back and forth in a small range of the middle position, and during the steering process, the steering wheel is adjusted greatly. During a steering maneuver, the steering wheel angle is used as an input and the vehicle response is manifested in yaw rate and lateral acceleration, wherein the yaw rate may reflect changes in the steering wheel angle and the relationship to vehicle speed. In the embodiment of the invention, compared with the traditional direct identification method utilizing the yaw rate signal, the method for identifying the steering process based on the short-time average energy of the yaw rate is insensitive to tiny and unconscious steering operation in the operation process of the driver, can more easily and accurately determine the starting point and the ending point of the actual steering operation of the driver, and has higher robustness.
Next, the identification of the driving behavior of the steering process is described.
In the embodiment of the invention, the identification of the driving condition in the steering process mainly comprises the identification of the turning driving condition, the identification of the turning driving condition and the identification of the lane changing driving condition.
The identification of the turning running condition and the U-turn running condition is determined by the change angle of the course angle in the steering process, and the identification method is as follows:
(1) and when the calculated course angle change angle is positioned in a first change interval, judging that the steering process belongs to the turning running working condition.
(2) And when the calculated course angle change angle is in a second change interval, judging that the steering process belongs to the U-turn driving working condition.
The change angle of the course angle in the steering process can be obtained by a GPS system, and can also be estimated by using the yaw velocity. Under the non-limiting condition, the vehicle heading angle change angle can be approximately calculated by the following formula (2):
wherein, omega is the vehicle yaw angular velocity, and the unit is DEG/s;the units are, as a vehicle heading angle, t1 and t2 denote a steering process start time and an end time.
In an embodiment of the invention, the first variation interval may be [75 °, 105 ° ], and the second variation interval is [150 °, 210 ° ].
Since the yaw rate variation during the lane change is relatively small, typically less than 10 °/s, while the yaw rate variation is greatly affected by the signal quality and the driver's manner of operation, it is difficult to identify the lane change to the course using the yaw rate alone. In addition, the change of the steering angle is stable in the lane changing process, and obvious regularity is presented. Based on the characteristic, the invention introduces a dynamic time warping algorithm to identify the lane change working condition. In addition, in order to improve the identification accuracy, the invention also introduces lateral displacement in the lane change working condition identification. That is, the lane-change driving condition of the embodiment of the present invention is identified based on the maximum yaw rate during the steering process, the sum of weighted distances between the course profile and the preset typical lane-change template curve, and the lateral displacement. Specifically, when the weighted distance sum is smaller than a preset weighted distance threshold, the maximum value of the yaw rate is smaller than a preset yaw rate threshold, and the lateral displacement is within a preset displacement range, it is determined that the steering process belongs to the lane-changing driving condition.
Wherein the yaw-rate maximum value is the maximum value of the yaw-rates detected by the sensors during the steering. The preset yaw-rate threshold may be 10/s.
The vehicle lateral displacement can be calculated by the following equation (3):
wherein,is the vehicle course angle, in degrees; v. ofxIs the vehicle speed, and the unit is m/s; y is the vehicle lateral displacement in m.
In the process of one-time steering, when the position of the vehicle is adjusted in the lane line, small lateral displacement may occur, and when the vehicle continuously crosses two lanes, large lateral displacement may occur. In consideration of the above scenario, lane width and vehicle width, in the embodiment of the present invention, the threshold range of the vehicle lateral displacement in the lane change condition recognition is set to [1.5m, 6.5m ].
The weighted distance sum is obtained based on a dynamic warping algorithm, and the specific calculation method is as follows:
(1) normalizing the course angle course curve in the steering process to obtain a normalized curve so as to eliminate the influence of the course angle amplitude and mainly focus on the change mode of the course angle in the course of changing the track; the processing can be performed using a commonly used normalization function.
(2) And carrying out dynamic time warping on the normalized curve and a typical lane changing template curve in a typical lane changing process based on actual data to obtain the weighted distance sum.
Because the step of calculating the weighted distance sum between the course angle history curve and the template curve by using the dynamic warping algorithm can refer to the existing dynamic warping algorithm, in order to avoid repeated description, the invention only explains the main steps and mainly comprises the following steps:
and opening a two-dimensional coordinate system by taking the characteristic vector A of the template curve and the sample point serial number I, J of the characteristic vector B of the normalized curve as coordinate axes, searching a point sequence C in the coordinate system, namely a time warping function, and mapping the sequence B to the sequence A. The feature vector a ═ { a1, a2, …, ai, …, am }, and the feature vector B ═ B1, B2, …, bj, …, bn }, B1, B2, …, bj, …, bn are angle values of the normalized course angle.
Let the time warping function C be:
C={c1,…,ck,…,cK}
ck=(ik,jk)
wherein ik is belonged to [1, n ], jk is belonged to [1, m ]
The time warping function needs to satisfy the following constraints:
(1) monotonic condition ik ≥ ik-1
(2) Continuous condition ik-ik-1 ≤ 1
(3) The boundary conditions i1, j1, 1, ik, m, jk, n
Other constraints include window conditions, slope conditions, etc., and are not described in detail herein.
The time warping function satisfying the above constraint conditions can project the sequence B onto the sequence a, there are usually a plurality of time warping functions, in order to evaluate the merits of different time warping functions, a distortion value evaluation index is introduced, and for the obtained time warping function, a local distortion value or a local matching distance is defined as:
d(ck)=‖aik-bjk‖
after the sequence a and the sequence B are mapped by the time warping function C, the sum of the weighted distances is:
where w (k) is a weighting function, which in one example may be equal weight, each portion being given a different weight to enhance the impact of certain features in the matching process.
The dynamic warping algorithm realizes the minimum sum of weighted distances through a local optimization method, and the final mapping function is as follows:
through the steps, the sum of the weighted distances between the course angle history curve and the preset typical lane changing template curve in the steering process can be obtained.
To sum up, the method for identifying the lateral driving condition of the vehicle provided by the embodiment of the invention firstly identifies the steering process, identifies the turning and turning-around driving conditions based on the course angle change angle when the effective steering process is identified, and identifies the lane-changing driving condition in the steering process based on the weighted distance sum between the course curve of the course angle and the preset typical lane-changing template curve, the maximum value of the yaw velocity and the lateral displacement, so that the identification method has good adaptability and high identification accuracy rate, the lane-changing driving condition precision rate in the lateral driving condition of the vehicle is up to more than 90 percent by utilizing the dynamic time warping algorithm, and the operation condition of the driver on the vehicle can be more accurately determined.
Based on the same inventive concept, the embodiment of the invention also provides a system for identifying the lateral driving condition of the vehicle, and as the principle of the problem solved by the system is similar to that of the method, the implementation of the system can refer to the implementation of the method, and repeated details are omitted.
As shown in fig. 3, the system for identifying the lateral driving condition of the vehicle according to the embodiment of the present invention includes:
the steering identification module 200 is used for identifying the steering process of the vehicle by using a preset steering identification method;
the working condition identification data calculation module 210 is configured to calculate the identified working condition identification data in the steering process, where the working condition identification data includes a heading angle change angle, a weighted distance sum between a heading angle history curve and a preset typical lane change template curve, a maximum yaw rate, and a lateral displacement; the weighted distance sum is obtained based on a dynamic warping algorithm;
and the driving condition identification module 220 is configured to determine, based on the calculated condition identification data, a driving condition to which the steering process belongs, where the driving condition includes a turning driving condition, and a lane changing driving condition, where the turning driving condition and the turning driving condition are identified based on the heading angle change angle, and the lane changing driving condition is identified based on a weighted distance sum, a yaw rate maximum value, and a lateral displacement.
Further, the steering identification module 200 specifically identifies the steering process of the vehicle by:
calculating the short-time average energy of the yaw velocity in the preset time at the first calculation moment;
recording the first calculation time as the starting time of the vehicle steering process when the average energy of the calculated yaw rate at the first calculation time is larger than a first set threshold value when the short-term average energy of the calculated yaw rate at the first calculation time is larger than the first set threshold value;
at the second calculation moment, calculating the short-time average energy of the yaw velocity in the preset time;
when the average energy of the short-term yaw rate calculated at the second calculation moment is smaller than a second set threshold value, recording the second calculation moment as the end time of the vehicle steering process;
the first set threshold is greater than the second set threshold.
Further, the preset time is 2 s; said first set threshold being 0.5(°/s)2(ii) a What is needed isThe second set threshold is 0.25(°/s)2。
Further, the driving condition identification module 220 is specifically configured to:
when the calculated course angle change angle is located in a first change interval, judging that the steering process belongs to a turning running working condition;
when the calculated course angle change angle is located in a second change interval, judging that the steering process belongs to a U-turn driving working condition;
when the weighted distance sum is smaller than a preset weighted distance threshold value, the maximum value of the yaw velocity is smaller than a preset yaw velocity threshold value, and the lateral displacement is within a preset displacement range, judging that the steering process belongs to a lane-changing driving working condition;
the first variation interval is smaller than the second variation interval.
Further, the first variation interval is [75 °, 105 ° ]; the second variation interval is [150 degrees, 210 degrees ]; the preset weighted distance threshold is 0.1; the preset yaw velocity threshold value is 10 degrees/s; the preset displacement range is [1.5m, 6.5m ].
The functions of the above modules may correspond to the corresponding processing steps in the flows shown in fig. 1 to 2, and are not described herein again.
The above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. A method of identifying a lateral driving condition of a vehicle, comprising:
recognizing the steering process of the vehicle by using a preset steering recognition method;
calculating the identified working condition identification data in the steering process, wherein the working condition identification data comprises a course angle change angle, a weighted distance sum between a course angle process curve and a preset typical lane changing template curve, a maximum yaw velocity and lateral displacement; the weighted distance sum is obtained based on a dynamic warping algorithm;
determining a driving condition to which the steering process belongs based on the calculated condition identification data, wherein the driving condition comprises a turning driving condition, a turning driving condition and a lane changing driving condition, the turning driving condition and the turning driving condition are identified based on the course angle change angle, and the lane changing driving condition is identified based on the weighted distance sum, the maximum yaw rate and the lateral displacement;
the method for recognizing the vehicle steering process by using the preset steering recognition method comprises the following steps:
calculating the short-time average energy of the yaw velocity in the preset time at the first calculation moment;
recording the first calculation time as the starting time of the vehicle steering process when the average energy of the calculated yaw rate at the first calculation time is larger than a first set threshold value when the short-term average energy of the calculated yaw rate at the first calculation time is larger than the first set threshold value;
at the second calculation moment, calculating the short-time average energy of the yaw velocity in the preset time;
when the average energy of the short-term yaw rate calculated at the second calculation moment is smaller than a second set threshold value, recording the second calculation moment as the end time of the vehicle steering process;
the calculation formula of the short-time average energy of the yaw angular velocity is as follows:
wherein E is the average energy of yaw angular velocity in short time, and the unit is (°/s)2Omega is a yaw angular velocity, which is obtained by a sensor, and has the unit of DEG/s, k is an average energy duration range, k is T/dt, dt is a time interval for sampling the yaw angular velocity, and T is preset time for calculating short-time average energy of the yaw angular velocity;
the first set threshold is greater than the second set threshold;
the determining the driving condition to which the steering process belongs based on the calculated condition identification data specifically includes:
when the calculated course angle change angle is located in a first change interval, judging that the steering process belongs to a turning running working condition;
when the calculated course angle change angle is located in a second change interval, judging that the steering process belongs to a U-turn driving working condition;
when the weighted distance sum is smaller than a preset weighted distance threshold value, the maximum value of the yaw velocity is smaller than a preset yaw velocity threshold value, and the lateral displacement is within a preset displacement range, judging that the steering process belongs to a lane-changing driving working condition;
the first variation interval is smaller than the second variation interval.
2. The method for identifying the lateral driving condition of the vehicle according to claim 1, wherein the preset time is 2 s; said first set threshold being 0.5(°/s)2(ii) a Said second set threshold being 0.25(°/s)2。
3. The method for identifying a lateral driving behavior of a vehicle according to claim 1, characterized in that the first variation interval is [75 °, 105 ° ]; the second variation interval is [150 degrees, 210 degrees ];
the preset weighted distance threshold is 0.1; the preset yaw velocity threshold value is 10 degrees/s; the preset displacement range is [1.5m, 6.5m ].
4. A system for identifying a lateral driving condition of a vehicle, comprising:
the steering identification module is used for identifying the steering process of the vehicle by using a preset steering identification method;
the operating condition identification data calculation module is used for calculating the identified operating condition identification data in the steering process, and the operating condition identification data comprises a course angle change angle, the sum of weighted distances between a course angle process curve and a preset typical lane change template curve, the maximum value of a yaw angular velocity and lateral displacement; the weighted distance sum is obtained based on a dynamic warping algorithm;
the driving condition identification module is used for determining the driving condition to which the steering process belongs based on the calculated working condition identification data, wherein the driving condition comprises a turning driving condition, a turning driving condition and a lane changing driving condition, the turning driving condition and the turning driving condition are identified based on the course angle change angle, and the lane changing driving condition is identified based on the weighted distance sum, the maximum yaw angular velocity and the lateral displacement;
the steering identification module specifically identifies the steering process of the vehicle through the following steps:
calculating the short-time average energy of the yaw velocity in the preset time at the first calculation moment;
recording the first calculation time as the starting time of the vehicle steering process when the average energy of the calculated yaw rate at the first calculation time is larger than a first set threshold value when the short-term average energy of the calculated yaw rate at the first calculation time is larger than the first set threshold value;
at the second calculation moment, calculating the short-time average energy of the yaw velocity in the preset time;
when the average energy of the short-term yaw rate calculated at the second calculation moment is smaller than a second set threshold value, recording the second calculation moment as the end time of the vehicle steering process;
the calculation formula of the short-time average energy of the yaw angular velocity is as follows:
wherein E is the average energy of yaw angular velocity in short time, and the unit is (°/s)2Omega is a yaw angular velocity, which is obtained by a sensor, and has the unit of DEG/s, k is an average energy duration range, k is T/dt, dt is a time interval for sampling the yaw angular velocity, and T is preset time for calculating short-time average energy of the yaw angular velocity;
the first set threshold is greater than the second set threshold;
the driving condition identification module is specifically used for:
when the calculated course angle change angle is located in a first change interval, judging that the steering process belongs to a turning running working condition;
when the calculated course angle change angle is located in a second change interval, judging that the steering process belongs to a U-turn driving working condition;
when the weighted distance sum is smaller than a preset weighted distance threshold value, the maximum value of the yaw velocity is smaller than a preset yaw velocity threshold value, and the lateral displacement is within a preset displacement range, judging that the steering process belongs to a lane-changing driving working condition;
the first variation interval is smaller than the second variation interval.
5. The system for identifying the lateral driving condition of the vehicle according to claim 4, wherein the preset time is 2 s; said first set threshold being 0.5(°/s)2(ii) a Said second set threshold being 0.25(°/s)2。
6. The system for identifying a vehicle lateral driving condition according to claim 4, wherein the first variation interval is [75 °, 105 ° ]; the second variation interval is [150 degrees, 210 degrees ]; the preset weighted distance threshold is 0.1; the preset yaw velocity threshold value is 10 degrees/s; the preset displacement range is [1.5m, 6.5m ].
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910152307.6A CN109878530B (en) | 2019-02-28 | 2019-02-28 | Method and system for identifying lateral driving condition of vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910152307.6A CN109878530B (en) | 2019-02-28 | 2019-02-28 | Method and system for identifying lateral driving condition of vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109878530A CN109878530A (en) | 2019-06-14 |
CN109878530B true CN109878530B (en) | 2021-04-06 |
Family
ID=66930065
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910152307.6A Active CN109878530B (en) | 2019-02-28 | 2019-02-28 | Method and system for identifying lateral driving condition of vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109878530B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110606092B (en) * | 2019-09-09 | 2021-05-18 | 中国第一汽车股份有限公司 | Method and device for determining driving state, vehicle and storage medium |
WO2022147785A1 (en) * | 2021-01-08 | 2022-07-14 | 华为技术有限公司 | Autonomous driving scenario identifying method and apparatus |
CN113247000B (en) * | 2021-07-16 | 2021-09-17 | 浙江所托瑞安科技集团有限公司 | Vehicle steering recognition method, device, equipment and storage medium |
CN114368388B (en) * | 2022-01-28 | 2024-05-03 | 中国第一汽车股份有限公司 | Driving behavior analysis method, device, equipment and storage medium |
CN114379560A (en) * | 2022-02-14 | 2022-04-22 | 中国第一汽车股份有限公司 | Method, device, storage medium and processor for determining vehicle working condition |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1627766B1 (en) * | 2004-08-17 | 2009-09-02 | Robert Bosch Gmbh | Driving assist system with lane changing recognition |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100209888A1 (en) * | 2009-02-18 | 2010-08-19 | Gm Global Technology Operations, Inc. | Vehicle stability enhancement control adaptation to driving skill based on curve-handling maneuvers |
CN103318181B (en) * | 2013-06-19 | 2015-07-15 | 电子科技大学 | Driver intention recognition method |
CN105718710B (en) * | 2014-12-02 | 2019-01-11 | 高德软件有限公司 | A kind of driving behavior analysis method and apparatus |
CN105389984A (en) * | 2015-11-16 | 2016-03-09 | 北京智视信息科技有限公司 | Driving behavior identification method based on mobile terminal sensing information fusion |
CN105574537B (en) * | 2015-11-23 | 2018-12-28 | 北京高科中天技术股份有限公司 | Dangerous driving behavior testing and evaluation method based on multisensor |
CN106218641B (en) * | 2016-08-04 | 2018-10-09 | 武汉理工大学 | A kind of vehicle new hand driver automatic identification and safe early warning method |
CN108515972B (en) * | 2018-03-30 | 2021-08-27 | 高新兴物联科技有限公司 | Driving behavior sensing method and system based on information fusion |
-
2019
- 2019-02-28 CN CN201910152307.6A patent/CN109878530B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1627766B1 (en) * | 2004-08-17 | 2009-09-02 | Robert Bosch Gmbh | Driving assist system with lane changing recognition |
Also Published As
Publication number | Publication date |
---|---|
CN109878530A (en) | 2019-06-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109878530B (en) | Method and system for identifying lateral driving condition of vehicle | |
CN109885066B (en) | Motion trail prediction method and device | |
Butakov et al. | Personalized driver/vehicle lane change models for ADAS | |
CN110596694A (en) | Complex environment radar multi-target tracking and road running environment prediction method | |
CN110834642B (en) | Vehicle deviation identification method and device, vehicle and storage medium | |
CN111381248B (en) | Obstacle detection method and system considering vehicle bump | |
CN111079590A (en) | Peripheral vehicle behavior pre-judging method of unmanned vehicle | |
CN110688877B (en) | Danger early warning method, device, equipment and storage medium | |
CN105774805A (en) | System for estimating lane and method thereof | |
EP3663152A1 (en) | Vehicle control device | |
CN105109484A (en) | Target-barrier determining method and device | |
US20050278112A1 (en) | Process for predicting the course of a lane of a vehicle | |
CN111599179B (en) | No-signal intersection vehicle motion planning method based on risk dynamic balance | |
CN112116100B (en) | Game theory decision method considering driver type | |
CN112249008B (en) | Unmanned automobile early warning method aiming at complex dynamic environment | |
Jeong et al. | Bidirectional long shot-term memory-based interactive motion prediction of cut-in vehicles in urban environments | |
CN106569214A (en) | Method and system for processing vehicle-mounted radar data of adaptive cruise vehicle in conjunction with navigation information | |
CN111325187B (en) | Lane position identification method and device | |
CN114475593B (en) | Travel track prediction method, vehicle, and computer-readable storage medium | |
CN111845737A (en) | Curve target identification method of intelligent vehicle and danger level judgment mechanism thereof | |
CN115923839A (en) | Vehicle path planning method | |
CN110834626B (en) | Driving obstacle early warning method and device, vehicle and storage medium | |
JP5682302B2 (en) | Traveling road estimation device, method and program | |
CN113158415B (en) | Vehicle track similarity evaluation method based on error analysis | |
CN116161048A (en) | Path generation method, device, equipment and 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 |