CN104442543A - Driver intension identification combining intelligent follow-up headlamp control system - Google Patents
Driver intension identification combining intelligent follow-up headlamp control system Download PDFInfo
- Publication number
- CN104442543A CN104442543A CN201410722987.8A CN201410722987A CN104442543A CN 104442543 A CN104442543 A CN 104442543A CN 201410722987 A CN201410722987 A CN 201410722987A CN 104442543 A CN104442543 A CN 104442543A
- Authority
- CN
- China
- Prior art keywords
- execution
- control system
- intelligent follow
- algorithm
- steering wheel
- 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
Abstract
The invention discloses a driver intension identification combining intelligent follow-up headlamp control system which comprises (1) a steering angle sensor and a vehicle velocity sensor, (2) a control algorithm, (3) a control algorithm execution ECU (Electronic Control Unit) 0, (4) a left headlamp lighting unit, (5) a left headlamp lighting unit execution ECU1, (6) a right headlamp lighting unit and (7) a right headlamp lighting unit execution ECU2. According to the system, HMM (Hidden Markov Model) parameters corresponding to emergency steering, normal steering and straight running working conditions under different vehicle velocities are optimized through a Baum-Welch algorithm according to acquired vehicle velocity and steering wheel steering angle data mainly by virtue of time sequence processing capability of an HMM and a strong foundation of statistics; then the running working conditions are identified in real time to predict a value of the steering angle sensor in the next time step, and the headlamp lighting units are controlled in advance according to the predicted steering angle value. Therefore, an AFS (Adaptive Front-lighting System) solution with high control accuracy, adaptability and real-time performance is implemented.
Description
Technical field
The invention belongs to technical field of automotive electronics, relate to a kind of intelligent follow-up headlight control system.
Background technology
The feature of automobile lamp itself determines the dependency to its car load.China's automobile lamp industry is development along with the development of auto-industry.Since reform and opening-up, through introducing technology, automobile lamp manufacture is undertaken designing by international advanced standard and is organized production, megatechnics transformation and pattern of enterprises transformation of the way restructuring, in the market competition of fierceness, China's automobile lamp industry technology level fast lifting in development.Some enterprises are researched and developed by the combination involving production, teaching & research, are provided with ability to develop independently.Along with maturation and the manufacturing development of Eltec, self-adapting following headlight system AFS is employed to come in some field more and more widely.
Existing AFS control technology have followed same technology path substantially: namely according to coherent signals such as steering wheel angle and fore suspension and rear suspension height, in conjunction with mathematical algorithm and control policy, realize the automatic adjustment to light.This technology path, can regulate light, but is limited to the algorithm computing relay time of car light group machine operation sluggishness and rotary angle transmitter, follows poor effect to needing the light of the environment such as large angle of turn.This defect has comparatively great impact to the design that China carries out AFS car light.In extreme circumstances, car light follow up speed cannot reach the designing requirement of AFS, may cause safety misadventure.
In order to overcome the above problems, provide one to prejudge chaufeur and turning to behavior, thus the intelligent follow-up headlight system realizing car light servo-actuated is in advance necessary.
Summary of the invention
For the problems referred to above, the object of this invention is to provide a kind of intelligent follow-up headlight control system in conjunction with driver intention identification.
Intelligent follow-up headlight control system in conjunction with driver intention identification provided by the invention, mainly by ability and the strong statistical basis of the process time series of HMM HMM, according to the data of the speed of a motor vehicle gathered, steering wheel angle and steering wheel angular velocity, by Baum-Welch algorithm to the emergency turn under the different speed of a motor vehicle, the parameter of normal direction of rotation and HMM model corresponding to straight-line travelling operating mode is optimized.Again real-time identification is carried out to driving cycle, the value of the rotary angle transmitter of prediction future time step, realize the control in advance to front car light lamp group according to prediction corner value.
System comprises:
Vehicle status sensor information;
Control algorithm and execution ECU0 thereof;
Left front headlight light group and execution ECU1 thereof
Right front headlight light group and execution ECU2 thereof.
Wherein, control algorithm mainly carries out computing to the vehicle status data such as the speed of a motor vehicle, rotary angle transmitter, define that system cloud gray model follows control policy;
Control algorithm ECU0: realize receiving speed information and rotary angle transmitter information from vehicle-mounted CAN bus, again according to rotary angle transmitter information calculated direction dish cireular frequency, carry out computing in conjunction with control algorithm, finally output a control signal to respectively and perform ECU1 and perform ECU2;
Perform ECU1 and perform ECU2: completing the light position signal according to control algorithm ECU0, respectively driving adjustment being carried out to the actuating device of front left headlight light group and front right headlight light group, and adjustment result feedback is returned control algorithm ECU0;
Accompanying drawing explanation
Fig. 1 is the system architecture schematic diagram of the intelligent follow-up headlight control system in conjunction with driver intention identification of the present invention.
Fig. 2 is that model of the present invention is determined and applies schematic diagram.
Fig. 3 is the schematic diagram of model construction of the present invention and prediction rotary angle transmitter data.
Specific embodiments
By the data of driving the experimental bench off-line collection speed of a motor vehicle, steering wheel angle and steering wheel angular velocity, after data prediction, with Baum-Welch algorithm to the emergency turn under the different speed of a motor vehicle, the parameter of normal direction of rotation and HMM model corresponding to straight-line travelling operating mode is optimized.Then by means of PXI1042 real-time controller and the driving experimental bench of National Instruments, in conjunction with assessment algorithm Forward-Backward algorithm and each multidimensional Gauss HMM model optimized of HMM, online real-time identification is carried out to driving cycle, and predict the value of the rotary angle transmitter that future time walks, carry out head light light group according to the value of prediction rotary angle transmitter and carry out pre-control, process as depicted in figs. 1 and 2.
Fig. 3 is for building multidimensional Gauss HMM model, i.e. the detailed process of the parameter of Confirming model.HMM model can by vectorial λ=[Q, N, II, a
ij, b
j(k)] describe.Wherein, Q={Q
1, Q
2..., Q
tmarkovian state in model, represent the little operation of the different brackets of certain steering operation under specific speed level; N is observed value number possible under each state correspondence; II is probability matrix, namely during t=1, and the probability that each state occurs; a
ij=P (s
i+l=q
j/ s
i=q
i) i, j=1,2 ..., N is the state transition probability from state i to state j; b
jk () is observed value probability matrix, be exactly under state i, produces the probability of observed value k.
Observed value probability matrix decision model is Discrete HMM, or continuous HMM.For Discrete HMM, b
jk () is the probability matrix of corresponding vector quantization code; For continuous HMM, b
jk () is the probability density function of description state i characteristic vector distribution.Consider that the steering wheel angle, steering wheel angular velocity and the car speed sensor signal that collect are all continuous signals, the signal distortion caused to prevent signal quantization, the HMM model that application multidimensional Gauss HMM model theory trains each driving cycles corresponding.Like this, b
j(k)=∑
m=1 ~ M{ c
imn [O, μ
im, U
im], 1≤i≤N.In formula, M is the number of the mixed components in observation sequence, herein total steering wheel angular velocity, steering wheel angle and the speed of a motor vehicle three mixed components.C
imit is the mixing constant of m the mixed components of corresponding states i.N [O, μ
im, U
im] be Gaussian function: μ
im, U
imbe respectively aviation value and the covariance of Gaussian function.O is observed value, O (t)={ a (t) can be stated as, b (t), c (t) }, wherein a (t), b (t), c (t) are respectively steering wheel angle, steering wheel angular velocity and the speed of a motor vehicle.
According to the steering wheel sensor signal O in certain vehicle speed range and the model initial parameter according to the acquisition of K-means algorithm, use the recurrence thought of Baum-Welch revaluation algorithm, adopt a kind of method of maximal possibility estimation, progressive alternate, the possibility P (O| λ) that observed value O is occurred relative to model λ increases gradually, until P (O| λ) converges to a definite value, λ is now required model parameter vector.
After the parameter of the multidimensional Gauss HMM model that each driving cycles of friction speed section is corresponding has all been optimized, application Farward-Backward algorithm, the steering wheel sensor data of Real-time Collection and the speed of a motor vehicle are assessed all multidimensional Gauss HMM models, select the multidimensional Gauss HMM of likelihood score maximum (possibility occurrence is maximum) as current driving cycles.
Choose the parameter of the multidimensional Gauss HMM model of corresponding current driving cycles, and add various contingent data after the sensing data that Real-time Collection is next, form prediction observation sequence collection.Application Forward-Backward algorithm, chooses the observation sequence that most probable occurs, thus dopes the steering wheel sensor value of future time step.
Claims (4)
1. the intelligent follow-up headlight control system in conjunction with driver intention identification, it is characterized in that: described system comprises car speed sensor, steering wheel angle sensor, control algorithm ECU0, execution ECU1 and execution ECU2: described control algorithm ECU0 and receives the data message of car speed sensor and steering wheel angle sensor by CAN, algorithm operation result is sent to respectively by CAN and performs the adjustment that ECU1 and execution ECU2 realizes light-illuminating angle.
2. a kind of intelligent follow-up headlight control system in conjunction with driver intention identification according to claim 1, it is characterized in that: the steering wheel angle sensor of vehicle, the signal of car speed sensor can be analog signals, also can be digital signal, be sent to CAN with digital signal form after treatment.
3. a kind of intelligent follow-up headlight control system in conjunction with driver intention identification according to claim 1, is characterized in that: described execution ECU1 and execution ECU2 respectively has two motor drive ics, realizes the adjustment to left and right directions, above-below direction.
4. a kind of intelligent follow-up headlight control system in conjunction with driver intention identification according to claim 1, is characterized in that: head light light group has the control motor that can realize left and right directions, above-below direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410722987.8A CN104442543A (en) | 2014-11-28 | 2014-11-28 | Driver intension identification combining intelligent follow-up headlamp control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410722987.8A CN104442543A (en) | 2014-11-28 | 2014-11-28 | Driver intension identification combining intelligent follow-up headlamp control system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104442543A true CN104442543A (en) | 2015-03-25 |
Family
ID=52889553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410722987.8A Pending CN104442543A (en) | 2014-11-28 | 2014-11-28 | Driver intension identification combining intelligent follow-up headlamp control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104442543A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106023344A (en) * | 2016-06-06 | 2016-10-12 | 清华大学 | Driving style estimation method based on driving pattern transition probability |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH082316A (en) * | 1994-06-21 | 1996-01-09 | Ichikoh Ind Ltd | Automatic control mechanism for automobile headlamp irradiation direction |
| US20040246730A1 (en) * | 2003-04-03 | 2004-12-09 | Kazuki Takahashi | Headlamp apparatus for vehicle |
| CN101049808A (en) * | 2007-03-12 | 2007-10-10 | 上海小糸车灯有限公司 | Self-adaptive control device for head light of auto car |
| CN202448822U (en) * | 2011-12-14 | 2012-09-26 | 长安大学 | Automobile self-adapting headlamp device based on singlechip |
| CN203472659U (en) * | 2013-01-29 | 2014-03-12 | 沈海红 | Full-featured adaptive front-lighting system used for automobile |
-
2014
- 2014-11-28 CN CN201410722987.8A patent/CN104442543A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH082316A (en) * | 1994-06-21 | 1996-01-09 | Ichikoh Ind Ltd | Automatic control mechanism for automobile headlamp irradiation direction |
| US20040246730A1 (en) * | 2003-04-03 | 2004-12-09 | Kazuki Takahashi | Headlamp apparatus for vehicle |
| CN101049808A (en) * | 2007-03-12 | 2007-10-10 | 上海小糸车灯有限公司 | Self-adaptive control device for head light of auto car |
| CN202448822U (en) * | 2011-12-14 | 2012-09-26 | 长安大学 | Automobile self-adapting headlamp device based on singlechip |
| CN203472659U (en) * | 2013-01-29 | 2014-03-12 | 沈海红 | Full-featured adaptive front-lighting system used for automobile |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106023344A (en) * | 2016-06-06 | 2016-10-12 | 清华大学 | Driving style estimation method based on driving pattern transition probability |
| CN106023344B (en) * | 2016-06-06 | 2019-04-05 | 清华大学 | Driving style estimation method based on driving mode transition probability |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tang et al. | Prediction-uncertainty-aware decision-making for autonomous vehicles | |
| CN108919795B (en) | Automatic driving automobile lane change decision method and device | |
| US10235881B2 (en) | Autonomous operation capability configuration for a vehicle | |
| CN102795225B (en) | Method for detecting disturbance state of driver by utilizing driver-side longitudinal control model | |
| CN103853908B (en) | A kind of maneuvering target tracking method of adaptive interaction formula multi-model | |
| Streubel et al. | Prediction of driver intended path at intersections | |
| US20190351899A1 (en) | Automated driving systems and control logic using sensor fusion for intelligent vehicle control | |
| US20190155291A1 (en) | Methods and systems for automated driving system simulation, validation, and implementation | |
| US9290186B2 (en) | Messaging via vehicle steering wheel | |
| CN106564496B (en) | Based on the preceding intelligent vehicle safety environment envelope reconstructing method to vehicle drive behavior | |
| CN103754221A (en) | Vehicle adaptive cruise control system | |
| Yu et al. | MPC-based regional path tracking controller design for autonomous ground vehicles | |
| CN105788360B (en) | A kind of methods, devices and systems of vehicle collision avoidance | |
| CN112249008B (en) | Unmanned automobile early warning method aiming at complex dynamic environment | |
| CN104608765A (en) | Intelligent overtaking method and system for automobile | |
| CN111845766A (en) | Method for automatically controlling automobile | |
| Koga et al. | Realization of different driving characteristics for autonomous vehicle by using model predictive control | |
| CN109572689A (en) | A kind of control method of finished and system based on radar cognitive disorders object | |
| CN108045373A (en) | A kind of automatic Pilot longitudinal direction unified planning method and system | |
| CN106218612B (en) | A kind of method, apparatus and terminal of vehicle safety travel | |
| Xu et al. | Design and implementation of driving control system for autonomous vehicle | |
| CN114523982A (en) | Speed planning method for automatic driving parallel driving avoidance | |
| CN104442543A (en) | Driver intension identification combining intelligent follow-up headlamp control system | |
| CN114664094B (en) | Vehicle track prediction method, device, chip, terminal and computer equipment | |
| CN112455439B (en) | Environment cognition and decision control method and system for unmanned vehicle and vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150325 |