CN115946704A - Driving style recognition method and device - Google Patents
Driving style recognition method and device Download PDFInfo
- Publication number
- CN115946704A CN115946704A CN202310081499.2A CN202310081499A CN115946704A CN 115946704 A CN115946704 A CN 115946704A CN 202310081499 A CN202310081499 A CN 202310081499A CN 115946704 A CN115946704 A CN 115946704A
- Authority
- CN
- China
- Prior art keywords
- driving style
- driving
- data
- vehicle
- current moment
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000004044 response Effects 0.000 claims abstract description 34
- 230000001133 acceleration Effects 0.000 claims description 115
- 238000012545 processing Methods 0.000 claims description 23
- 238000012935 Averaging Methods 0.000 claims description 16
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 8
- 238000013139 quantization Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 230000006399 behavior Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000011897 real-time detection Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 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
- Y02T10/80—Technologies aiming to reduce greenhouse gasses emissions common to all road transportation technologies
- Y02T10/84—Data processing systems or methods, management, administration
Landscapes
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The application provides a driving style identification method and a driving style identification device, which comprise the following steps: acquiring vehicle driving data at the current moment; determining whether the vehicle driving data at the current moment is effective data influencing the driving style; determining a driving style index value at the current moment based on the vehicle driving data at the current moment in response to the vehicle driving data at the current moment being valid data; determining a driving style quantized value at the current moment based on the driving style index value at the current moment and the driving style index value at the historical moment; determining a driving style quantized value at the current time based on a driving style index value at a historical time in response to the driving data of the vehicle at the current time not being valid data; and determining the driving style at the current moment based on the driving style quantized value at the current moment. The method can realize the quasi-real-time recognition of the driving style of the driver, and the accuracy of the recognition result and the recognition efficiency are higher.
Description
Technical Field
The application relates to the technical field of vehicles, in particular to a driving style identification method and device.
Background
The driving style refers to a behavior feature exhibited in driving activities of a driver determined by stable characteristics such as driving skills and driving preferences of the driver, and is externally represented as a driving habit having individual or group differences in the driving behaviors. The driving style has important influence on various performances such as safety, comfort and energy conservation of the closed-loop system of the human car. With the intelligent development of vehicle-mounted electric control systems, it has become a trend to optimize the design of driving systems and control systems according to the driving style so as to realize individual self-adaptation to drivers. In order to realize the above-mentioned optimization design, it is very important to accurately recognize the driving style of the driver.
In the related art, the driving style of a driver is generally analyzed using a subjective recognition method such as questionnaire or using an objective statistical method that relies on complete driving cycle data.
However, the current driving style identification method is difficult to determine the driving style of the driver in real time, and also difficult to ensure the authenticity and the globality of the identification result.
Disclosure of Invention
In view of this, the present application provides a method and an apparatus for identifying a driving style, which can implement quasi real-time identification of a driving style of a driver, and have higher accuracy of an identification result and higher efficiency of identification.
Specifically, the method comprises the following technical scheme:
in one aspect, a driving style recognition method is provided, and the method includes:
acquiring vehicle driving data at the current moment;
determining whether the vehicle driving data at the current moment is effective data influencing the driving style;
determining a driving style index value at the current time based on the vehicle driving data at the current time in response to the vehicle driving data at the current time being valid data, the driving style index value indicating a tendency of a driving style;
determining a driving style quantization value at the current moment based on the driving style index value at the current moment and the driving style index value at the historical moment, wherein the driving style index value at the historical moment is the driving style index value determined based on the historical effective data;
determining a driving style quantized value at the current time based on the driving style index value at the historical time in response to the driving data of the vehicle at the current time not being valid data;
and determining the driving style at the current moment based on the driving style quantized value at the current moment.
Optionally, the obtaining of the vehicle driving data at the current time includes:
acquiring original vehicle driving data at the current moment;
and carrying out low-pass filtering processing on the driving parameter signal containing the original vehicle driving data at the current moment to obtain the filtered vehicle driving data at the current moment.
Optionally, the vehicle driving data comprises longitudinal acceleration and lateral acceleration; the determining whether the vehicle driving data at the current moment is effective data influencing the driving style comprises the following steps:
calculating an acceleration norm based on the longitudinal acceleration and the lateral acceleration;
responding to the acceleration norm larger than a preset threshold value, and determining the vehicle driving data at the current moment as effective data influencing the driving style;
and in response to the acceleration norm being smaller than or equal to the preset threshold, determining that the vehicle driving data at the current moment is not effective data influencing the driving style.
Optionally, the vehicle driving data further includes a vehicle speed; the determining the driving style index value at the current time based on the vehicle driving data at the current time comprises:
determining a maximum vehicle speed value in a working condition level corresponding to the vehicle speed, wherein the working condition level indicates a level corresponding to a vehicle speed interval where the vehicle speed is located;
correcting the vehicle speed based on the maximum vehicle speed value to obtain a corrected vehicle speed;
calculating an acceleration phase based on the longitudinal acceleration and the lateral acceleration;
and correcting the acceleration norm based on the corrected vehicle speed and the acceleration phase, and taking the corrected acceleration norm as the index value of the driving style at the current moment.
Optionally, the correcting the acceleration norm based on the corrected vehicle speed and the acceleration phase includes: correcting the acceleration norm according to the following formula:
DS(k)＝a xy ×sin(β)×v'，
wherein DS (k) is the corrected acceleration norm, a xy The vehicle speed is corrected by correcting the vehicle speed v.
Optionally, the determining the quantized value of the driving style at the current time based on the driving style index value at the current time and the driving style index value at the historical time includes:
and carrying out averaging processing on the driving style index value at the current moment and the driving style index value at the historical moment, and taking the calculated average as the driving style quantized value at the current moment.
Optionally, the averaging processing is performed on the driving style index value at the current time and the driving style index value at the historical time, and includes:
and carrying out averaging processing on the driving style index value at the current moment and the historical latest S-1 driving style index values, wherein S is an integer greater than or equal to 2.
Optionally, the determining the quantized value of the driving style at the current time based on the driving style index value at the historical time in response to the driving data of the vehicle at the current time not being valid data includes:
and in response to the fact that the vehicle driving data at the current moment are not valid data, abandoning the vehicle driving data at the current moment, carrying out averaging processing on S driving style index values which are most recent historically, and taking the calculated average value as the driving style quantized value at the current moment, wherein S is an integer greater than or equal to 2.
Optionally, the determining the driving style at the current moment based on the driving style quantized value at the current moment includes:
and inquiring the mapping relation between the pre-stored driving style quantized value and the driving style according to the driving style quantized value at the current moment to obtain the driving style at the current moment.
In another aspect, an embodiment of the present application provides a driving style recognition apparatus, where the apparatus includes:
the acquisition module is used for acquiring vehicle driving data at the current moment;
a determination module to:
determining whether the vehicle driving data at the current moment is effective data influencing the driving style;
determining a driving style index value at the current time based on the vehicle driving data at the current time in response to the vehicle driving data at the current time being valid data, the driving style index value indicating a tendency of a driving style;
determining a driving style quantized value at the current moment based on the driving style index value at the current moment and the driving style index value at the historical moment, wherein the driving style index value at the historical moment is the driving style index value determined based on the historical effective data;
in response to the vehicle driving data at the current time not being valid data, determining a driving style quantized value at the current time based on the driving style index value at the historical time;
and determining the driving style at the current moment based on the driving style quantized value at the current moment.
The embodiment of the application provides a driving style identification method and a driving style identification device, wherein the method judges whether the acquired vehicle driving data at the current moment is effective data influencing the driving style, only when the acquired vehicle driving data at the current moment is the effective data, the driving style index value at the current moment is determined based on the vehicle driving data at the current moment, the driving style at the current moment is comprehensively determined based on the driving style index value at the current moment and the driving style index value at the historical moment, and when the vehicle driving data at the current moment is the ineffective data, the driving style at the current moment is directly determined based on the driving style index value at the historical moment, so that the adverse influence of the ineffective data on the identification result can be avoided, the accuracy of the identification result and the identification efficiency are improved, in addition, the driving style at the current moment is determined according to the driving style quantization value at the current moment, and the quasi-real-time detection of the driving style is realized.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a first driving style identification method provided in an embodiment of the present application;
fig. 2 is a flowchart of a second driving style identification method provided in an embodiment of the present application;
fig. 3 is a flowchart of a third driving style identification method provided in the embodiment of the present application;
fig. 4 is a flowchart of a fourth driving style identification method provided in the embodiment of the present application;
fig. 5 is a schematic diagram of a driving style recognition apparatus according to an embodiment of the present application.
Specific embodiments of the present application have been shown by way of example in the drawings and will be described in more detail below. These drawings and written description are not intended to limit the scope of the inventive concepts in any manner, but rather to illustrate the inventive concepts to those skilled in the art by reference to specific embodiments.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
Unless defined otherwise, all technical terms used in the examples of the present application have the same meaning as commonly understood by one of ordinary skill in the art.
Firstly, in order to facilitate understanding of the technical solutions provided by the present application, the research ideas of the inventors are briefly introduced here:
after intensive research on application scenes and the like of the driving style, the inventor finds that if the driving style is applied to a vehicle-mounted electric control system, the method for identifying the driving style can meet the following three requirements: (1) The universality, the information required for driving style identification is derived from vehicle-mounted CAN (Controller Area Network, CAN for short) signals or more general vehicle-mounted external sensors, such as an IMU (Inertial Measurement Unit, IMU for short) and a GPS (Global Positioning System, GPS for short), so as to facilitate the deployment and application of the method on commercial vehicles; (2) The method comprises the following steps that (1) the vehicle-mounted electric control system is quasi-real-time, and in view of the fact that the vehicle-mounted electric control system is suitable for drivers of different types and the driving style of the same driver evolving along with time, the driving style is identified as a vehicle-mounted quasi-real-time process, so that the vehicle-mounted electric control system can timely acquire the change of the driver style and can be matched with corresponding system configuration in a certain driving period; (3) Globally, the lack of information coverage dimension usually leads to the recognition of local driving style, and in addition, the interference of various internal and external factors often increases the deviation between the recognition result and the real driving style, so that the authenticity and the global property of the recognition result can be ensured by the comprehensive information coverage dimension.
Obviously, neither the subjective identification method using questionnaire in the related art nor the objective statistical method relying on complete driving cycle data can satisfy the above requirements at the same time. The inventor proposes the following driving style recognition method and device in consideration of versatility, quasi-real-time performance, and globality.
In order to make the technical solutions and advantages of the present application clearer, the following will describe the embodiments of the present application in further detail with reference to the accompanying drawings.
In a first aspect, an embodiment of the present application provides a driving style identification method. The method can be implemented by a global controller such as a vehicle controller or a special controller such as a chassis pre-controller, which is hereinafter referred to as a controller. Referring to fig. 1, the method includes:
step 101: and acquiring the vehicle driving data at the current moment.
In this step, since the various sensors of the vehicle are electrically connected to the controller, the controller can receive the driving data of the vehicle at the current time transmitted by the various sensors.
Step 102: it is determined whether the driving data of the vehicle at the present time is effective data that affects the driving style.
In practice, various conditions exist during the running of the vehicle, but the determination of the driving style is often dependent on the operation of the user under some specific conditions. For example, the vehicle may be operated at a constant speed, and the user operation is relatively simple and smooth, but this does not indicate that the driving style of the user is "smooth". Therefore, in order to improve the effectiveness of the driving style recognition, the vehicle driving data can be evaluated and screened, and after certain preprocessing, the subsequent driving style recognition is carried out. In this step, the controller may evaluate the vehicle driving data at the current time according to a preset algorithm to determine whether the vehicle driving data at the current time is effective data that affects the driving style. Alternatively, the driving data of the vehicle when the conditions such as acceleration and deceleration or steering operation occur may be determined as effective data that affects the driving style.
Step 103: in response to the vehicle driving data at the present time being valid data, a driving style index value at the present time is determined based on the vehicle driving data at the present time, the driving style index value indicating a tendency of a driving style.
In this step, after the current vehicle driving data is determined to be valid, a driving style index value indicating a tendency of the driving style of the user corresponding to the current vehicle driving data may be determined based on the current vehicle driving data. Furthermore, the driving style of the user can be comprehensively recognized subsequently by means of the driving style index values at the current time and the historical time.
Step 104: and determining the driving style quantized value at the current moment based on the driving style index value at the current moment and the driving style index value at the historical moment, wherein the driving style index value at the historical moment is the driving style index value determined based on the historical effective data.
In this step, the driving style quantization value at the current time may be determined according to the driving style index value at the current time and the driving style index value at the historical time, so as to realize quantization of the conceptual index of the driving style. It should be noted that the driving style values at the historical time are determined based on the historical effective data, which may be the driving data of the vehicle historically evaluated as effective data by step 102. The driving style value at the historical time may be calculated from the historical effective data temporarily when step 104 is performed, or may be read directly from the vehicle memory. The vehicle memory may store therein the driving data of the vehicle evaluated as the valid data each time, or directly store therein driving style index values at historical times calculated from the historical valid data.
Step 105: in response to the driving data of the vehicle at the current time not being valid data, a driving style quantized value at the current time is determined based on the driving style index value at the historical time.
In this step, if the vehicle driving data at the current time is not valid data, the driving style quantization value at the current time may be determined directly based on the driving style index value at the historical time. Namely, if the judgment result shows that the vehicle driving data at the current moment is not effective data influencing the driving style, the driving style is considered to be not changed temporarily, and the vehicle driving data at the current moment is ignored, so that the accuracy and the effectiveness of the driving style identification result are prevented from being reduced.
Step 106: and determining the driving style at the current moment based on the driving style quantized value at the current moment.
In this step, after the quantized value of the driving style at the current time is determined, the driving style at the current time can be determined based on the quantized value of the driving style, and the conversion from the quantized value to the driving style is realized. The controller can pre-store response logics corresponding to different driving styles, determine the corresponding response logics according to the determined driving style at the current moment, and respond to user operation according to the response logics matched with the current driving style, so that the vehicle can adapt to individual drivers.
In summary, the driving style identification method provided by the embodiment of the application can realize quantitative identification of the driving style, which is a virtual concept. In the identification process, invalid data in the data for identifying the driving style are removed, so that the accuracy and the effectiveness of the driving style identification are ensured, the driving style at the current moment can be determined always according to the quantized value of the driving style at the current moment, and the quasi-real-time performance of the driving style identification is ensured.
In some embodiments, referring to fig. 2, step 101 may comprise:
step 1011: and acquiring the original vehicle driving data at the current moment.
The original vehicle driving data in this step can be data directly detected by various sensors in the vehicle and transmitted to the controller.
Step 1012: and carrying out low-pass filtering processing on the driving parameter signal containing the original vehicle driving data at the current moment to obtain the filtered vehicle driving data at the current moment. The driving parameter signal may be, for example, an acceleration signal or a vehicle speed signal.
Since various high-frequency noises such as electromagnetic interference are often mixed in signals output by various sensors of the vehicle, the high-frequency noises are ineffective for identifying the driving style, and may interfere with the identification of the driving style. In addition, medium-high frequency interference information is stored in the vehicle parameter signal due to environmental disturbances such as continuous deceleration strips, sudden forward or side wind, or sudden road depressions, which are difficult to avoid during driving. And the response of the vehicle when the driver drives normally is generally in a low frequency range (only aiming at common drivers and excluding special groups such as racing drivers) determined by the physiological characteristics and the driving habits of the driver. For low-frequency interference caused by long slope or constant wind, the low-frequency response brought by the operation of the driver is fused and represented as the final response of the vehicle, which is the basis for the driver to decide the next operation, so the low-frequency interference can be used as a part of the representation of the driving style.
Therefore, in this step, the medium-high frequency information in the driving parameter signal is removed to avoid the interference of the driving style recognition. In addition, the low-pass filtering processing can also realize the smooth processing of the driving parameter signals in effect, and is beneficial to accurately determining effective data in the later period.
Optionally, a low-pass filter with a cut-off frequency of 2Hz is used for filtering the driving parameter signal containing the original vehicle driving data at the current moment, and the filtered vehicle driving data at the current moment is used for subsequent driving style recognition, so that the interference of the interference signal on the recognition result can be effectively avoided, and the accuracy of the recognition result is improved.
In some embodiments, the vehicle driving data includes longitudinal acceleration and lateral acceleration. Referring to fig. 3, step 102, comprises:
step 1021: based on the longitudinal acceleration and the lateral acceleration, an acceleration norm is calculated.
Alternatively, the acceleration norm may be calculated using the following formula:
Step 1022: and judging whether the acceleration norm is larger than a preset threshold value.
In this step, the preset threshold is set empirically or obtained by statistical analysis of a large amount of acceleration data. The preset threshold represents the minimum value of the total norm of the longitudinal acceleration and the lateral acceleration of the vehicle when the driving operation of the driver causes the vehicle to have the working conditions of acceleration, deceleration, steering and the like. The preset threshold value here is generally not 0 because the vehicle also has some degree of acceleration fluctuation when traveling at a straight constant speed. Alternatively, the preset threshold may be 0.03g, where g is the acceleration of gravity. That is, in this step, a may be xy The size was determined with 0.03 g. By executing the step, whether the vehicle is currently subjected to the working conditions such as acceleration, deceleration or steering, which can be used for identifying the driving style, can be determined.
Step 1023: and in response to the acceleration norm being larger than a preset threshold value, determining the vehicle driving data at the current moment as effective data influencing the driving style.
In this step, if the acceleration norm is greater than the preset threshold, it may be determined that the vehicle is subjected to conditions such as acceleration, deceleration, or steering due to the driver's operation, and the vehicle driving data at this time may be used to extract an index value of the driving style of the driver, so that the vehicle driving data at the current time is determined as effective data affecting the driving style.
Step 1024: and in response to the acceleration norm being less than or equal to a preset threshold, determining that the vehicle driving data at the current moment is not effective data influencing the driving style.
In this step, if the acceleration norm is less than or equal to the preset threshold, it may be determined that the driving style of the driver cannot be reflected by the vehicle driving data at the current time, and it may be determined that the driving style is not affected by the vehicle driving data.
In some embodiments, the inventors contemplate the following: firstly, the acceleration in the vehicle driving parameters is extremely important for identifying the driving style, for aggressive drivers, the ultimate adhesion capability of the tire is generally utilized to the maximum and continuously, the external expression is that the acceleration and the deceleration are both aggressive, and for prudent drivers, the vehicle is generally controlled to run in a gentler manner, so that the acceleration norm can directly reflect the driving style; secondly, the longitudinal acceleration and the lateral acceleration also have different weights in terms of embodying the driving style; thirdly, the vehicle speed is the most important and intuitive index for describing the running state of the vehicle, and the vehicle speed and the change state thereof can also reflect the driving style of the driver to a certain extent. On the basis of the three aspects, the acceleration norm is provided as a core index for identifying the driving style, and the acceleration norm is assisted and corrected by means of the vehicle speed and the acceleration phase, so that the driving style is identified by using more diversified information, and the globality of identifying the driving style is improved.
Specifically, the vehicle driving data further includes a vehicle speed.
Referring to fig. 4, step 103 may include:
step 1031: and determining the maximum vehicle speed value in the working condition level corresponding to the vehicle speed, wherein the working condition level indicates the level corresponding to the vehicle speed interval where the vehicle speed is located.
Although the vehicle speed may be somewhat related to the driving style of the driver, the vehicle speed may not be directly used to determine the driving style of a driver due to differences in the maximum vehicle speed limits for different driving areas by traffic regulations. For example, when one driver drives on an expressway at an average speed of 110km/h and the other driver drives on an urban road at an average speed of 70km/h, the former driver cannot be considered as being more "aggressive" than the latter driver in driving style. In contrast, the driving style of a driver with an average driving speed of 70km/h on an urban road is more likely to be "aggressive" than the driving style of a driver on an urban road but with an average driving speed of 60 km/h. Therefore, the connotation of the vehicle speed index is very rich.
In the embodiment, the vehicle speed is divided into a plurality of intervals, and each interval corresponds to one working condition level so as to improve the comparability between different vehicle speeds by means of the working condition levels. Specifically, the vehicle speed may be divided into a plurality of intervals according to a plurality of different maximum vehicle speed limits in the traffic regulation. For example, there are different types of road speed limits in traffic regulations: 30. 50, 60, 70, 80, 100, 110, and 120, the vehicle speed may be divided into [0, 30), [30, 50), [50, 60), [60, 70), [70, 80), [80, 100), [100, 120), and [120, ∞ ], corresponding to operating range 1-8, respectively. The interval division and the operating condition level are only examples, and can be adjusted according to requirements in practice. For example, the vehicle speed can be divided into two working condition levels of 0-90km/h and 90-120 km/h on the basis of dividing a typical urban road and an expressway. Or, a large amount of original vehicle speed data and a driving style obtained by labeling and the like can be obtained, a plurality of vehicle speed interval division thresholds are obtained through cluster analysis, and the vehicle speed interval and the working condition level are divided based on the plurality of vehicle speed interval division thresholds. For the vehicle speeds under different working condition levels, the vehicle speeds can be used for driving style identification after certain processing, and for the same working condition level, the vehicle speeds are direct embodiment of the driving style.
On this basis, in step 1031, the maximum vehicle speed value in the operating condition level corresponding to the current vehicle speed, that is, the maximum vehicle speed value in the vehicle speed interval in which the current vehicle speed is located, may be determined, so as to correct the vehicle speed by means of the maximum vehicle speed value, so that the vehicle speeds under different operating condition levels may all be compared with each other.
Step 1032: and correcting the vehicle speed based on the maximum vehicle speed value to obtain a corrected vehicle speed.
In this step, the vehicle speed can be corrected by using the following formula:
v'＝v/v max-n where v represents a vehicle speed, v' is a corrected vehicle speed obtained by correcting the vehicle speed v, v max-n And representing the maximum vehicle speed value in the nth working condition level, wherein n is the working condition level corresponding to the vehicle speed interval where the current vehicle speed is located.
In this step, the vehicle speed is corrected, so that the vehicle speed index can be compared with each other and the driving style can be more accurately represented.
Step 1033: based on the longitudinal acceleration and the lateral acceleration, an acceleration phase is calculated.
In this step, the acceleration phase may be calculated by using the following formula:
β＝tan -1 (|a x |/|a y | in which β is the acceleration phase。
After the acceleration phase is obtained through calculation in the step, the acceleration norm can be corrected by means of the acceleration phase, so that the driving style index value can reflect different influence degrees of longitudinal acceleration and lateral acceleration on the driving style.
Step 1034: and correcting the acceleration norm based on the corrected vehicle speed and the acceleration phase, and taking the corrected acceleration norm as the driving style index value at the current time.
In the step, the corrected acceleration norm is used as the driving style index value at the current moment, so that the driving style is quantized, and the acceleration norm is corrected by correcting the vehicle speed and the acceleration phase, so that the accuracy of the driving style index value is ensured.
Optionally, step 1034 may include: correcting the acceleration norm according to the following formula:
DS(k)＝a xy ×sin(β)×v'，
wherein DS (k) is the corrected acceleration norm, a xy The vehicle speed is corrected by correcting the vehicle speed v.
Since the driving style is more aggressive when the acceleration norm is larger than the working condition level (which has been verified in the related art), the acceleration norm is corrected by introducing the acceleration norm so that the corrected acceleration norm more accurately represents the driving style of the driver. It should be noted that, mathematically, although the introduction of sin (β) changes the true value of the acceleration norm, the acceleration norm indicators of all the driver groups are corrected, and the driving style recognition is the comparison of the relative trends of these indicators, so the deviation caused by the correction can be mutually offset in the driving style recognition process, and the introduction of sin (β) can not reduce the accuracy of the driving style recognition result, but can improve the accuracy of the driving style recognition result.
In some embodiments, step 104 comprises:
and carrying out averaging processing on the driving style index value at the current time and the driving style index value at the historical time, and taking the calculated average as the driving style quantized value at the current time.
In the embodiment, the mean value of the driving style index value at the current time and the driving style index value at the historical time is used as the driving style quantized value at the current time, so that the quantized value of the driving style is influenced by the driving style index value at the current time and the driving style index value at the historical time, the driving style is recognized according to the comprehensive expression of the driver in a long time period, and the reliability of the driving style recognition result is improved.
Optionally, the averaging processing is performed on the driving style index value at the current time and the driving style index value at the historical time, and includes:
and carrying out averaging processing on the driving style index value at the current moment and the historical latest S-1 driving style index values, wherein S is an integer greater than or equal to 2.
The method is characterized in that only the driving style index value at the current moment and S-1 historically latest driving style index values are acquired to calculate the quantized driving style value at the current moment, so that the driving style is always identified based on the latest limited driving style index values, and the calculation efficiency of the quantized driving style value and the effectiveness and the quasi-real-time performance of the driving identification result are ensured.
In some embodiments, step 105 comprises:
and in response to the fact that the vehicle driving data at the current time are not valid data, abandoning the vehicle driving data at the current time, carrying out averaging processing on S driving style index values which are most recent historically, and taking the calculated average value as a driving style quantized value at the current time, wherein S is an integer greater than or equal to 2.
That is, if the current vehicle driving data is not valid data, it is considered that the driving style of the driver cannot be represented by the operation behavior of the driver at the current time, and the current vehicle driving data is discarded. Since it is considered that the driving style quantized value of the driver at this time is not changed from the previous time, the average of S driving style index values which are most recent in history is directly used as the driving style quantized value at the current time.
That is, in the present embodiment, the closest S driving style quantized values are selected by using a moving window function with a width of S, and the average value is calculated as the driving style quantized value at the current time, that is:
wherein DS (t) is the driving style quantified value at the current moment, and->
The driving style index value corresponding to the kth effective data is taken as the latest driving style index value in the moving window, and the average index value is obtained by combining the driving style index values corresponding to the previous S-1 effective data, DS (i) is the driving style index value corresponding to the ith effective data, and the value range of i is [ k-S, k]. If the vehicle driving data at the current moment is valid data, the window function covers the driving style index value at the current moment and S-1 historical latest driving style index values; if the vehicle driving data at the current time is not valid data, the window function covers the S driving style index values that are most recent in history.
In some embodiments, step 106 comprises:
and inquiring the mapping relation between the pre-stored driving style quantized value and the driving style according to the driving style quantized value at the current moment to obtain the driving style at the current moment.
In the vehicle controller or the memory, a mapping relationship between the driving style quantized value and the driving style may be stored in advance, and the mapping relationship may be set empirically, or obtained by calibration, or determined by other effective methods. After determining the quantized value of the driving style at the current time, the controller may obtain the driving style at the current time directly based on the mapping relationship, output the driving style at the current time, or determine a response logic corresponding to the driving style at the current time according to the driving style at the current time, and respond to the user operation with the response logic.
In summary, the driving style identification method provided by the embodiment of the application can be used for identifying based on vehicle driving data such as acceleration and vehicle speed, so that the method can be applied to any vehicle, only the vehicle is required to be provided with a sensor for detecting the acceleration and the vehicle speed, and the vehicle is convenient to deploy on a commodity vehicle; for the obtained vehicle driving data, noise information irrelevant to driving style recognition is removed by using a low-pass filter, so that the recognition efficiency and the recognition result accuracy are improved; the effectiveness of the vehicle driving data is identified by using the index of the acceleration norm, and the driving style is identified by using the effective data, so that the efficiency and the accuracy of identifying the driving style are further improved; the vehicle speed is used for distinguishing working condition levels, the vehicle speeds of different working condition levels are corrected, the acceleration norm is corrected by means of the corrected vehicle speed and the acceleration phase, so that the driving style quantized value can more accurately represent the driving style, more parameters are introduced to identify the driving style, the comprehensiveness of information coverage is ensured, and the identification result is closer to the real global driving style; in addition, the moving window is used for carrying out averaging processing on the latest S driving style index values, so that the driving style quantized value can more accurately reflect the driving style of the latest driver, the driving style at the current moment can be output in real time, quasi-real-time operation of driving style identification is realized, and the driving style identification method is convenient to apply to a vehicle-mounted electric control system.
On the other hand, the embodiment of the application provides a driving style recognition device. Referring to fig. 5, the apparatus includes:
an obtaining module 200, configured to obtain vehicle driving data at a current moment;
a determining module 300 configured to:
determining whether the vehicle driving data at the current moment is effective data influencing the driving style;
determining a driving style index value at the current time based on the vehicle driving data at the current time in response to the vehicle driving data at the current time being valid data, the driving style index value indicating a tendency of a driving style;
determining a driving style quantized value at the current moment based on the driving style index value at the current moment and the driving style index value at the historical moment, wherein the driving style index value at the historical moment is the driving style index value determined based on the historical effective data;
determining a driving style quantized value at the current time based on a driving style index value at a historical time in response to the driving data of the vehicle at the current time not being valid data;
and determining the driving style at the current moment based on the quantized value of the driving style at the current moment.
Optionally, the obtaining module 200 is further configured to:
acquiring original vehicle driving data at the current moment;
and carrying out low-pass filtering processing on the driving parameter signal containing the original vehicle driving data at the current moment to obtain the vehicle driving parameters at the current moment after filtering processing.
Optionally, the vehicle driving data comprises longitudinal acceleration and lateral acceleration; the determination module 300 is further configured to:
calculating an acceleration norm based on the longitudinal acceleration and the lateral acceleration;
in response to the acceleration norm being larger than a preset threshold, determining the vehicle driving data at the current moment as effective data influencing the driving style;
and in response to the acceleration norm being less than or equal to a preset threshold, determining that the vehicle driving data at the current moment is not effective data influencing the driving style.
Optionally, the vehicle driving data further includes vehicle speed; the determination module 300 is further configured to:
determining a maximum vehicle speed value in a working condition level corresponding to the vehicle speed, wherein the working condition level indicates a level corresponding to a vehicle speed interval where the vehicle speed is located;
correcting the vehicle speed based on the maximum vehicle speed value to obtain a corrected vehicle speed;
calculating an acceleration phase based on the longitudinal acceleration and the lateral acceleration;
and correcting the acceleration norm based on the corrected vehicle speed and the acceleration phase, and taking the corrected acceleration norm as the driving style index value at the current time.
Optionally, the determining module 300 is further configured to: correcting the acceleration norm according to the following formula:
DS(k)＝a xy ×sin(β)×v'，
wherein DS (k) is the corrected acceleration norm, a xy The vehicle speed is corrected by correcting the vehicle speed v.
Optionally, the determining module 300 is further configured to:
and carrying out averaging processing on the driving style index value at the current time and the driving style index value at the historical time, and taking the calculated average as the driving style quantized value at the current time.
Optionally, the determining module 300 is further configured to:
and carrying out averaging processing on the driving style index value at the current moment and the historical latest S-1 driving style index values, wherein S is an integer greater than or equal to 2.
Optionally, the determining module 300 is further configured to:
and in response to the fact that the vehicle driving data at the current time are not valid data, abandoning the vehicle driving data at the current time, carrying out averaging processing on S driving style index values which are most recent historically, and taking the calculated average value as a driving style quantized value at the current time, wherein S is an integer greater than or equal to 2.
Optionally, the determining module 300 is further configured to:
and inquiring the mapping relation between the pre-stored driving style quantized value and the driving style according to the driving style quantized value at the current moment to obtain the driving style at the current moment.
It should be noted that the apparatus provided in this embodiment corresponds to the foregoing method embodiment, and each module can be used to implement each step in the foregoing method embodiment, and details of each step are not repeated here. Also, the division of the modules is merely exemplary, and in some embodiments, the driving style recognition device may be further divided into: the driving style recognition method comprises a data preprocessing module, an effective working condition detection module, an index extraction module, a driving style recognition module and the like, wherein each module respectively executes partial steps in the method embodiment so as to realize the recognition of the driving style together. For example, the data preprocessing module is used for eliminating medium-high frequency invalid information and high-frequency noise information which are irrelevant to driving style recognition in the original vehicle driving parameter signal by adopting a low-pass filter, and filtering and smoothing the vehicle driving parameter signal; the effective working condition detection module is used for detecting a data segment which is effective to the driving style identification from the filtered vehicle driving data, and the data segment is called as effective data; the index extraction module determines a working condition level according to the vehicle speed, corrects the vehicle speed according to the working condition level, and fuses an acceleration norm index, an acceleration phase index and a vehicle speed index into a unified driving style quantization index DS; the driving style module carries out driving style recognition by setting a movable window and detecting a driving style index value corresponding to the effective data in the window, so that the quasi-real-time operation of the driving style recognition is realized.
In summary, the present application provides a driving style recognition apparatus, which determines whether acquired current vehicle driving data is valid data that affects a driving style, determines a driving style index value at the current time based on the current vehicle driving data only when the acquired current vehicle driving data is valid data, and comprehensively determines a current driving style based on the current driving style index value and a driving style index value at a historical time, and determines the current driving style based on the driving style index value at the historical time when the current vehicle driving data is invalid data, so that the invalid data can be prevented from adversely affecting a recognition result, accuracy of the recognition result and recognition efficiency can be improved, and the driving style at the current time is determined always according to a driving style quantization value at the current time, thereby realizing quasi-real-time detection of the driving style.
In this application, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The term "plurality" means two or more unless expressly limited otherwise.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the present application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only.
It will be understood that the present application is not limited to the precise arrangements that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. A driving style recognition method, characterized in that the method comprises:
acquiring vehicle driving data at the current moment;
determining whether the vehicle driving data at the current moment is effective data influencing the driving style;
determining a driving style index value at the current time based on the vehicle driving data at the current time in response to the vehicle driving data at the current time being valid data, the driving style index value indicating a tendency of a driving style;
determining a driving style quantized value at the current moment based on the driving style index value at the current moment and the driving style index value at the historical moment, wherein the driving style index value at the historical moment is the driving style index value determined based on the historical effective data;
in response to the vehicle driving data at the current time not being valid data, determining a driving style quantized value at the current time based on the driving style index value at the historical time;
and determining the driving style at the current moment based on the driving style quantized value at the current moment.
2. The method of claim 1, wherein the obtaining vehicle driving data at a current time comprises:
acquiring original vehicle driving data at the current moment;
and carrying out low-pass filtering processing on the driving parameter signal containing the original vehicle driving data at the current moment to obtain the filtered vehicle driving data at the current moment.
3. The method of claim 1, wherein the vehicle driving data comprises longitudinal acceleration and lateral acceleration; the determining whether the vehicle driving data at the current moment is effective data influencing the driving style comprises the following steps:
calculating an acceleration norm based on the longitudinal acceleration and the lateral acceleration;
responding to the acceleration norm larger than a preset threshold value, and determining the vehicle driving data at the current moment as effective data influencing the driving style;
and in response to the acceleration norm being smaller than or equal to the preset threshold, determining that the vehicle driving data at the current moment is not effective data influencing the driving style.
4. The method of claim 3, wherein the vehicle driving data further includes vehicle speed; the determining the driving style index value at the current time based on the vehicle driving data at the current time comprises:
determining a maximum vehicle speed value in a working condition level corresponding to the vehicle speed, wherein the working condition level indicates a level corresponding to a vehicle speed interval where the vehicle speed is located;
correcting the vehicle speed based on the maximum vehicle speed value to obtain a corrected vehicle speed;
calculating an acceleration phase based on the longitudinal acceleration and the lateral acceleration;
and correcting the acceleration norm based on the corrected vehicle speed and the acceleration phase, and taking the corrected acceleration norm as the index value of the driving style at the current moment.
5. The method of claim 4, wherein said modifying the acceleration norm based on the modified vehicle speed and the acceleration phase comprises: correcting the acceleration norm according to the following formula:
DS(k)＝a xy ×sin(β)×v'，
wherein DS (k) is the corrected acceleration norm, a xy The vehicle speed is corrected by correcting the vehicle speed v.
6. The method according to claim 1, wherein the determining the driving style quantized value at the current time based on the driving style index value at the current time and the driving style index value at a historical time comprises:
and carrying out averaging processing on the driving style index value at the current moment and the driving style index value at the historical moment, and taking the calculated average as the driving style quantized value at the current moment.
7. The method according to claim 6, wherein the averaging of the driving style index value at the current time and the driving style index value at a historical time comprises:
and carrying out averaging processing on the driving style index value at the current moment and the historical latest S-1 driving style index values, wherein S is an integer greater than or equal to 2.
8. The method according to claim 1, wherein the determining the driving style quantization value for the current time based on the driving style index value for the historical time in response to the driving data of the vehicle at the current time not being valid data comprises:
and in response to the fact that the vehicle driving data at the current moment are not valid data, abandoning the vehicle driving data at the current moment, carrying out averaging processing on S driving style index values which are most recent historically, and taking the calculated average value as the driving style quantized value at the current moment, wherein S is an integer greater than or equal to 2.
9. The method of claim 1, wherein determining the driving style at the current time based on the quantized driving style value at the current time comprises:
and inquiring the mapping relation between the pre-stored driving style quantized value and the driving style according to the driving style quantized value at the current moment to obtain the driving style at the current moment.
10. A driving style recognition apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring vehicle driving data at the current moment;
a determination module to:
determining whether the vehicle driving data at the current moment is effective data influencing the driving style;
determining a driving style index value at the current time based on the vehicle driving data at the current time in response to the vehicle driving data at the current time being valid data, the driving style index value indicating a tendency of a driving style;
determining a driving style quantized value at the current moment based on the driving style index value at the current moment and the driving style index value at the historical moment, wherein the driving style index value at the historical moment is the driving style index value determined based on the historical effective data;
determining a driving style quantized value at the current time based on the driving style index value at the historical time in response to the driving data of the vehicle at the current time not being valid data;
and determining the driving style at the current moment based on the driving style quantized value at the current moment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310081499.2A CN115946704A (en) | 2023-01-16 | 2023-01-16 | Driving style recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310081499.2A CN115946704A (en) | 2023-01-16 | 2023-01-16 | Driving style recognition method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115946704A true CN115946704A (en) | 2023-04-11 |
Family
ID=87289418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310081499.2A Pending CN115946704A (en) | 2023-01-16 | 2023-01-16 | Driving style recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115946704A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230227046A1 (en) * | 2022-01-14 | 2023-07-20 | Toyota Motor North America, Inc. | Mobility index determination |
| CN117056799A (en) * | 2023-08-03 | 2023-11-14 | 广东省机场管理集团有限公司工程建设指挥部 | Processing method, device, equipment and medium for vehicle sensor data |
-
2023
- 2023-01-16 CN CN202310081499.2A patent/CN115946704A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230227046A1 (en) * | 2022-01-14 | 2023-07-20 | Toyota Motor North America, Inc. | Mobility index determination |
| CN117056799A (en) * | 2023-08-03 | 2023-11-14 | 广东省机场管理集团有限公司工程建设指挥部 | Processing method, device, equipment and medium for vehicle sensor data |
| CN117056799B (en) * | 2023-08-03 | 2024-03-26 | 广东省机场管理集团有限公司工程建设指挥部 | Processing method, device, equipment and medium for vehicle sensor data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108995653B (en) | Method and system for identifying driving style of driver | |
| CN101949704B (en) | Reliability evaluation device, reliability evaluation method | |
| CN115946704A (en) | Driving style recognition method and device | |
| US9669833B2 (en) | Method and system for operating adaptive cruise control system | |
| US7177750B2 (en) | System for influencing the speed of a motor vehicle | |
| EP2690423B1 (en) | Vehicle data analysis apparatus, vehicle data analysis method, and defect diagnosis apparatus | |
| KR102011008B1 (en) | System and method for detecing a road state | |
| CN112519788B (en) | Method and device for determining driving style and automobile | |
| CN112009486A (en) | Driving control method, system and device and automobile | |
| CN109436085A (en) | A kind of wire-controlled steering system gearratio control method based on driving style | |
| CN107225928A (en) | A kind of active/passive suspension modes handover control system and method based on driving behavior | |
| CN116588078B (en) | Vehicle control method, device, electronic equipment and computer readable storage medium | |
| CN111688700A (en) | Driving mode switching system, method and device and storage medium | |
| CN114103966A (en) | Control method, device and system for driving assistance | |
| CN115195856B (en) | Steering power assisting method and device and vehicle | |
| JP7302411B2 (en) | Driving skill evaluation device | |
| CN115476861A (en) | Safety evaluation system of intelligent networked automobile | |
| US7831368B2 (en) | System for influencing the speed of a motor vehicle | |
| CN113022235A (en) | Tire positioning method, device, equipment, storage medium and tire pressure monitoring method | |
| CN112319487A (en) | Electronic throttle control mode adjusting method based on driving habits of driver | |
| CN120024325B (en) | Automatic obstacle avoidance method and system for intelligent connected vehicle | |
| CN117734655B (en) | Real-time brake pedal force prompting method and device, electronic equipment and storage medium | |
| CN118372612B (en) | In-vehicle air conditioner optimal control method and system based on out-of-vehicle temperature monitoring | |
| CN110723153A (en) | Individualized driving habit learning system based on environmental information and vehicle motion | |
| CN115447616B (en) | Method and device for generating objective index of vehicle driving |
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 |