CN109249932B - Vehicle acceleration model calibration method and acceleration intention identification method and device - Google Patents
Vehicle acceleration model calibration method and acceleration intention identification method and device Download PDFInfo
- Publication number
- CN109249932B CN109249932B CN201710575602.3A CN201710575602A CN109249932B CN 109249932 B CN109249932 B CN 109249932B CN 201710575602 A CN201710575602 A CN 201710575602A CN 109249932 B CN109249932 B CN 109249932B
- Authority
- CN
- China
- Prior art keywords
- acceleration
- accped
- vehicle
- rate
- spd
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2510/00—Input parameters relating to a particular sub-units
- B60W2510/06—Combustion engines, Gas turbines
- B60W2510/0604—Throttle position
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2510/00—Input parameters relating to a particular sub-units
- B60W2510/06—Combustion engines, Gas turbines
- B60W2510/0604—Throttle position
- B60W2510/0609—Throttle change rate
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Transportation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Mechanical Engineering (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
A vehicle acceleration model calibration method and an acceleration intention identification method and device are provided, the scheme is based on real vehicle operation during calibration, a computer is used for fitting the relation between an accelerator opening AccPed _ Norm, an accelerator change Rate AccPed _ Rate and a vehicle speed V _ Spd and an acceleration a, and different threshold values are set based on the numerical value of the acceleration a, so that an acceleration model is established and used for acceleration intention identification. The parameter acquisition that this scheme relates to is easy, and the calculated amount is little, and the acceleration model of establishing is simple reliable.
Description
Technical Field
The invention relates to a vehicle acceleration model calibration method, an acceleration intention identification method and a device thereof, belonging to the technical field of driving intention identification.
Background
Most of the current methods for identifying the intention of the driver are on a pure software level, and the intention of the driver is mainly identified by using intelligent algorithms such as fuzzy control, Mapedif, neural network and other intelligent control schemes.
For example, chinese patent document CN 103318181 a discloses a driver intention recognition method, which recognizes the behavior and intention of a driver based on a multidimensional discrete hidden markov model.
The intelligent algorithms are usually large in calculation amount when an acceleration model for intention recognition is established, the corresponding acceleration prediction process is quite complex, the requirement on hardware in actual application is high, occupied resources are large, and meanwhile cost is increased.
Disclosure of Invention
The invention aims to provide a vehicle acceleration model calibration method, an acceleration intention identification method and a device thereof, which are used for solving the problems of high hardware requirement, large resource occupation and higher cost caused by large calculation amount of the acceleration model and complex acceleration identification process in the prior art.
In order to achieve the above object, the scheme of the invention comprises:
the invention discloses a vehicle acceleration model calibration method, which comprises the following steps:
fitting the relation between the accelerator opening AccPed _ Norm, the accelerator change Rate AccPed _ Rate and the vehicle speed V _ Spd and the acceleration a;
and dividing at least two threshold value ranges according to the numerical value of the acceleration a, wherein each threshold value range corresponds to a corresponding acceleration control strategy.
Further, the threshold ranges are (0, d1], (d1, d2], (d2, + ∞),. The acceleration strategy is slow acceleration when 0 < a ≦ d1, general acceleration when d1 < a ≦ d2, and emergency acceleration when a > d 2.
Further, fitting AccPed _ Norm, throttle change Rate AccPed _ Rate and vehicle speed V _ Spd, and the relation of the acceleration a
K1 × AccPed _ Norm + k2 × AccPed _ Rate + k3 × V _ Spd; wherein k1, k2 and k3 are constant values.
Further, the tool used for processing is a matlabbcftool fitting tool box.
The invention relates to an acceleration intention identification method, which comprises the following steps:
1) acquiring the accelerator opening AccPed _ Norm, the accelerator change Rate AccPed _ Rate and the vehicle speed V _ Spd of the vehicle in real time during the running of the vehicle;
2) calculating an acceleration identification value a' by a first formula;
3) and executing a corresponding acceleration strategy according to the threshold value range falling into the a'.
Further, the first formula is:
a' ═ k1 × AccPed _ Norm + k2 × AccPed _ Rate + k3 × V _ Spd; wherein k1, k2 and k3 are constant values.
Further, the threshold ranges are (0, d1], (d1, d2], (d2, + ∞),. The acceleration strategy is slow acceleration when 0 < a ≦ d1, general acceleration when d1 < a ≦ d2, and emergency acceleration when a > d 2.
The invention relates to an acceleration intention recognition device, a processor and a memory, wherein the processor is used for executing instructions stored in the memory to realize the following method:
1) acquiring the accelerator opening AccPed _ Norm, the accelerator change Rate AccPed _ Rate and the vehicle speed V _ Spd of the vehicle in real time during the running of the vehicle;
2) calculating an acceleration identification value a' by a first formula;
3) and executing a corresponding acceleration strategy according to the threshold value range falling into the a'.
Further, the first formula is:
a' ═ k1 × AccPed _ Norm + k2 × AccPed _ Rate + k3 × V _ Spd; wherein k1, k2 and k3 are constant values.
Further, the threshold ranges are (0, d1], (d1, d2], (d2, + ∞),. The acceleration strategy is slow acceleration when 0 < a ≦ d1, general acceleration when d1 < a ≦ d2, and emergency acceleration when a > d 2.
The invention has the beneficial effects that:
in addition, the parameter acquisition related to the invention is easy, the calculated amount is small, and the established acceleration model is simple and reliable. The corresponding acceleration recognition has low requirements on a control chip of a vehicle in actual application, can effectively reduce the cost and the development difficulty for mass-production vehicle types, and is safe and reliable.
Drawings
FIG. 1 is a flow chart of a method for calibrating a vehicle acceleration model.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
As shown in fig. 1, a flowchart of a calibration method for a vehicle acceleration model is provided, where the off-line development and calibration stage specifically includes the following steps:
1) based on a vehicle with a fixed load, a large amount of working condition data are collected, and the influence of three factors, namely accelerator opening AccPed _ Norm, accelerator change Rate AccPed _ Rate and vehicle speed V _ Spd, on vehicle acceleration a is found out through combing and analyzing the data. The action rule of the operation intention of the driver can be found out according to the rule, and the sequence of the output signals in the whole process is shown as follows: the accelerator opening AccPed _ Norm is changed, then the accelerator change Rate AccPed _ Rate is changed, and finally the change of the vehicle acceleration a and the vehicle speed V _ Spd is reflected. It can be seen from the sampling data that within 0.1 second after the accelerator opening degree is changed, the accelerator change rate reaches a peak value (maximum value or minimum value), then the acceleration a reaches the peak value after delaying for about 1.2 seconds, and the vehicle acceleration change trend is mainly related to the accelerator opening degree, but has a certain relation with the accelerator change rate and the vehicle speed.
2) Through matlabbcftool fitting toolbox, three influencing factors are input, and the fitting acceleration function is as follows: and a, k1 × AccPed _ Norm + k2 × AccPed _ Rate + k3 × V _ Spd (after the function is confirmed, k1, k2 and k3 are fixed values), obtaining a vehicle acceleration model, quantifying or classifying the intention of the driver according to the acceleration value of the vehicle, and selecting a control related parameter set or different control modes according to the identified intention of the driver, so that the optimal control is achieved.
3) The obtained acceleration a is divided into three classes according to the driving intention by experience, and the threshold value sets are (0, d1, d2), (1) emergency acceleration when the a is larger than d2, (2) normal acceleration when the a is between d1 and d2, and (3) slow acceleration when the a is between 0 and d 1.
The acceleration intention identification method specifically comprises the following steps:
1) in the real-time running process of the vehicle, the vehicle control unit collects the accelerator opening AccPed _ Norm _ real, the accelerator change Rate AccPed _ Rate _ real and the vehicle speed V _ Spd _ real in real time;
2) the numerical values are substituted into a formula k1 multiplied by AccPed _ Norm + k2 multiplied by AccPed _ Rate + k3 multiplied by V _ Spd in a calibration stage to obtain an acceleration identification value a';
3) corresponding control regimes and parameters for slow acceleration strategies are executed when 0 < a ' ≦ d1, for general acceleration when d1 < a ' ≦ d2, and for emergency acceleration when a ' > d 2.
The basic scheme embodied in the above examples is:
when the calibration is developed off line, calculating characteristic parameters by a first method, dividing at least two threshold value ranges according to the obtained characteristic parameter values, wherein each threshold value range corresponds to a corresponding acceleration control strategy; when the vehicle runs in real time, the characteristic parameters are calculated according to the first method, and corresponding acceleration measures are executed when the characteristic parameters fall into a threshold range.
In this embodiment, the first method is to fit the accelerator opening, the accelerator change rate, and the speed to a function of the acceleration a by using a computer: k1 × AccPed _ Norm + k2 × AccPed _ Rate + k3 × V _ Spd, and the acceleration a is the characteristic parameter.
Claims (3)
1. A vehicle acceleration model calibration method is characterized by comprising the following steps:
1) based on a vehicle with a fixed load, acquiring a large amount of working condition data, and finding out the influence of three factors, namely accelerator opening AccPed _ Norm, accelerator change Rate AccPed _ Rate and vehicle speed V _ Spd, on vehicle acceleration a through combing and analyzing the data; the action rule of the operation intention of the driver can be found out according to the rule, and the sequence of the output signals in the whole process is shown as follows: firstly, the accelerator opening AccPed _ Norm changes, then the accelerator change Rate AccPed _ Rate changes, and finally the change of the vehicle acceleration a and the vehicle speed V _ Spd is reflected;
2) through matlabbcftool fitting toolbox, three influencing factors are input, and the fitting acceleration function is as follows: k1 × AccPed _ Norm + k2 × AccPed _ Rate + k3 × V _ Spd, wherein k1, k2 and k3 are fixed values, a vehicle acceleration model is obtained, then the intention of a driver is quantized or classified according to the acceleration value of the vehicle, and a relevant parameter set or different control modes are selected through the identified intention of the driver, so that the optimal control is achieved;
3) the obtained acceleration a is divided into three classes according to the driving intention by experience, and the threshold value sets are (0, d1, d2), (1) emergency acceleration when the a is larger than d2, (2) normal acceleration when the a is between d1 and d2, and (3) slow acceleration when the a is between 0 and d 1.
2. An acceleration intention recognition method, characterized by comprising the steps of:
1) acquiring the accelerator opening AccPed _ Norm, the accelerator change Rate AccPed _ Rate and the vehicle speed V _ Spd of the vehicle in real time during the running of the vehicle;
2) substituting the value obtained in step 1) into the formula described in claim 1: calculating an acceleration recognition value a' from k1 × AccPed _ Norm + k2 × AccPed _ Rate + k3 × V _ Spd;
3) executing a corresponding acceleration strategy according to the threshold range a' falls in claim 1.
3. An accelerated intent recognition apparatus comprising a processor, a memory, wherein the processor is configured to execute instructions stored in the memory to implement a method comprising:
1) acquiring the accelerator opening AccPed _ Norm, the accelerator change Rate AccPed _ Rate and the vehicle speed V _ Spd of the vehicle in real time during the running of the vehicle;
2) substituting the value obtained in step 1) into the formula described in claim 1: calculating an acceleration recognition value a' from k1 × AccPed _ Norm + k2 × AccPed _ Rate + k3 × V _ Spd;
3) executing a corresponding acceleration strategy according to the threshold range a' falls in claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710575602.3A CN109249932B (en) | 2017-07-14 | 2017-07-14 | Vehicle acceleration model calibration method and acceleration intention identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710575602.3A CN109249932B (en) | 2017-07-14 | 2017-07-14 | Vehicle acceleration model calibration method and acceleration intention identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109249932A CN109249932A (en) | 2019-01-22 |
| CN109249932B true CN109249932B (en) | 2020-10-20 |
Family
ID=65051815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710575602.3A Active CN109249932B (en) | 2017-07-14 | 2017-07-14 | Vehicle acceleration model calibration method and acceleration intention identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109249932B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113492868A (en) * | 2020-04-02 | 2021-10-12 | 广州汽车集团股份有限公司 | Automobile acceleration intention identification method and device, automobile and computer readable storage medium |
| CN113204742A (en) * | 2021-05-11 | 2021-08-03 | 雄狮汽车科技(南京)有限公司 | Vehicle control parameter calibration method and device and vehicle |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102010027730A1 (en) * | 2010-04-14 | 2011-10-20 | Bayerische Motoren Werke Aktiengesellschaft | Hybrid vehicle i.e. car, has control unit communicatively coupled with environment identifier sensor, where environment identifier sensor enables drive control based on sensor data and comprises radar sensor |
| CN103206524A (en) * | 2013-03-29 | 2013-07-17 | 北京经纬恒润科技有限公司 | Gear-shifting control method of automatic gear box |
| CN103277503A (en) * | 2013-05-17 | 2013-09-04 | 安徽江淮汽车股份有限公司 | Method and system for identifying kickdown intention of automatic speed changing vehicle driver |
| CN105946861A (en) * | 2016-06-02 | 2016-09-21 | 大连理工大学 | NAR neural network vehicle speed prediction method based on driving intention recognition |
| CN106168542A (en) * | 2016-07-06 | 2016-11-30 | 广州汽车集团股份有限公司 | ONLINE RECOGNITION method, system and the vehicle of a kind of vehicle working condition |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105644563B (en) * | 2015-12-22 | 2018-03-16 | 广州汽车集团股份有限公司 | A kind of throttle transient condition driving evaluation method and system |
-
2017
- 2017-07-14 CN CN201710575602.3A patent/CN109249932B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102010027730A1 (en) * | 2010-04-14 | 2011-10-20 | Bayerische Motoren Werke Aktiengesellschaft | Hybrid vehicle i.e. car, has control unit communicatively coupled with environment identifier sensor, where environment identifier sensor enables drive control based on sensor data and comprises radar sensor |
| CN103206524A (en) * | 2013-03-29 | 2013-07-17 | 北京经纬恒润科技有限公司 | Gear-shifting control method of automatic gear box |
| CN103277503A (en) * | 2013-05-17 | 2013-09-04 | 安徽江淮汽车股份有限公司 | Method and system for identifying kickdown intention of automatic speed changing vehicle driver |
| CN105946861A (en) * | 2016-06-02 | 2016-09-21 | 大连理工大学 | NAR neural network vehicle speed prediction method based on driving intention recognition |
| CN106168542A (en) * | 2016-07-06 | 2016-11-30 | 广州汽车集团股份有限公司 | ONLINE RECOGNITION method, system and the vehicle of a kind of vehicle working condition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109249932A (en) | 2019-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112519788B (en) | Method and device for determining driving style and automobile | |
| CN110949386B (en) | Vehicle adaptive cruise control system and method capable of recognizing driving tendency | |
| CN110949393B (en) | Driving behavior analysis method and device, vehicle and storage medium | |
| CN109249932B (en) | Vehicle acceleration model calibration method and acceleration intention identification method and device | |
| CN107369635B (en) | Intelligent semiconductor equipment system based on deep learning | |
| CN110386144B (en) | GHMM/GGAP-RBF hybrid model for identifying driver braking intention and identification method | |
| CN109249933B (en) | Driver acceleration intention identification method and device | |
| Gao et al. | Identification of cutting chatter through deep learning and classification | |
| CN113401123A (en) | Automobile prediction cruise parameter self-tuning control system fusing driving mode information | |
| CN111340074A (en) | Driver braking intention identification method based on improved RBF neural network | |
| CN113297249A (en) | Slow query statement identification and analysis method and device and query statement statistical method and device | |
| CN109743200B (en) | Resource feature-based cloud computing platform computing task cost prediction method and system | |
| KR20200046815A (en) | Radar signal classification method using HMM and neural networks | |
| CN116242636A (en) | Hardware-in-loop system for intelligent automobile chassis simulation test | |
| CN115307721A (en) | Method, device and equipment for evaluating quality of automobile acceleration sound and storage medium | |
| CN113722108A (en) | Container resource elastic pre-stretching method based on application operation load data prediction | |
| CN102831105B (en) | A kind of method of EXCEL and MINITAB15 software programming *-R control chart coefficient table | |
| CN116151385A (en) | Robot autonomous learning method based on generation of countermeasure network | |
| Gao et al. | MATLAB simulation of performance evaluation model of time-frequency analysis method based on SVM | |
| CN113435320B (en) | Human body posture estimation method with multiple models configured in self-adaption mode | |
| CN117922538B (en) | Measurement and control method and system for hybrid electric vehicle based on digital twin technology | |
| CN117785844A (en) | Automatic database optimization method based on up-down Wen Beishe S optimization | |
| CN113044046B (en) | Driver style recognition method, system, electronic device and readable storage medium | |
| CN118133208B (en) | Robot polishing offline identification abnormal data integration optimization system | |
| US20230035069A1 (en) | Method for training a neural network |
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 | ||
| CP03 | Change of name, title or address |
Address after: 450061 Yudao Road, Guancheng District, Zhengzhou City, Henan Province Patentee after: Yutong Bus Co., Ltd Address before: 450016 Yutong Industrial Zone, eighteen Li River, Henan, Zhengzhou Patentee before: Zhengzhou Yutong Bus Co., Ltd |
|
| CP03 | Change of name, title or address |