CN102795225B - Method for detecting disturbance state of driver by utilizing driver-side longitudinal control model - Google Patents
Method for detecting disturbance state of driver by utilizing driver-side longitudinal control model Download PDFInfo
- Publication number
- CN102795225B CN102795225B CN201210333693.7A CN201210333693A CN102795225B CN 102795225 B CN102795225 B CN 102795225B CN 201210333693 A CN201210333693 A CN 201210333693A CN 102795225 B CN102795225 B CN 102795225B
- Authority
- CN
- China
- Prior art keywords
- chaufeur
- vehicle
- driving
- steering wheel
- model
- 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.)
- Expired - Fee Related
Links
Landscapes
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides a method for detecting a disturbance state of a driver by utilizing a driver model. The method comprises the following steps: obtaining driving environment information of an automobile by an external sensor and judging a driving intention according to a ration between the position of the automobile and a lane boundary; when the driving intention is to keep the lane, calculating a change volume of a turning angle of a steering wheel by the driver model according to the driving environment information and the automobile state information and calculating and outputting an opening degree of an accelerator according to the present automobile speed and an expected longitudinal acceleration confirmed by a time interval between the automobile and the front automobile; when the driving intention is to change the lane, calculating the change volume of the turning angle of the steering wheel by the driver model according to the driving environment information and the state information and calculating and outputting the opening degree of the accelerator according to the present automobile speed and the expected longitudinal acceleration calculated on the basis of a lateral acceleration; comparing the turning angle of the steering wheel and the opening degree of the accelerator calculated by the driver model with a practical control data of the driver obtained by an internal sensor and judging if the driver is disturbed; and repeating the steps till stopping.
Description
Technical field
The present invention relates to a kind of method utilizing driver side longitudinal Comprehensive Control model inspection chaufeur disturbance state.The method is in the interference of detection chaufeur, utilize the chaufeur control data (steering wheel angle and accelerator open degree) under the current driving environment of pilot model real-time simulation, the control data of the control data of pilot model and true chaufeur is compared, and whether is interfered according to comparative result identification chaufeur.The hardware cost of the method is low, and recognition accuracy is high, is specially adapted to the DAS (Driver Assistant System) developing vehicle.
Background technology
Chaufeur is disturbed (such as, absent-minded, eat ,/the beverage that drinks water, make a phone call and passenger's chat and use onboard system etc.) be the major reason causing traffic accident, therefore be necessary to develop the disturbance state that method of inspection detects chaufeur in real time, to remind chaufeur in time in conjunction with traffic, reduce or avoid the generation of accident.
The detection of current chaufeur interference mainly concentrates on and utilizes the physiology of chaufeur to characterize, and such as, motion by constantly following the trail of eyes judges whether chaufeur is subject to vision interference etc.Although the physiology of chaufeur characterizes the situation that can embody chaufeur and be disturbed, but also there is very strong duplicity, such as when chaufeur is subject to interference (such as the thinking problem when driving) of cognitive aspect, the facial expression of chaufeur may not have anything to change, and is difficult to detect for the existing method of such interference.On the contrary, chaufeur then can reflect driver status truly to the controlling behavior of vehicle, and control data when research shows chaufeur control data under normal circumstances and is disturbed has very large difference.
Summary of the invention
The object of this invention is to provide a kind of new mode detecting chaufeur interference, the method utilizes pilot model, chaufeur controlling behavior under the current driving environment of real-time simulation, by the control data of the control data and true chaufeur that compare pilot model real-time simulation, can judge whether chaufeur is interfered exactly.
According to object of the present invention, a kind of pilot model comprises: path planning module, receive from the driving-environment information of onboard exterior sensors, the driving intention (change or keep track) of decision-making chaufeur, plan corresponding driving trace, and constantly revise according to car body position in real time; Take aim at module in advance, the characteristic of taking aim in advance according to the described data separate chaufeur from path planning module obtains expected trajectory data; Prediction module, obtains prediction locus data according to the status information from vehicle dynamic model; First comparing module, receives expected trajectory data and prediction locus data, and obtains lateral deviation data by the comparison of these two track datas; Side direction control module, outputs to the second comparing module and longitudinal control module respectively according to described lateral deviation direction data calculation dish corner knots modification and lateral acceleration by it; Longitudinal control module, according to described lateral acceleration calculation expectation longitudinal acceleration, then according to expecting longitudinal acceleration calculation of throttle opening value and exporting vehicle dynamic model to; Second comparing module, according to the current steering wheel angle of described steering wheel angle knots modification and vehicle dynamic model, calculates final steering wheel angle and exports vehicle dynamic model to.
According to object of the present invention, a kind of method utilizing above-mentioned pilot model to detect chaufeur disturbance state is proposed, described method comprises: step a, the driving-environment information of vehicle is obtained by onboard exterior sensors, by comparing the relation of current vehicle position and residing lane boundary, judge that chaufeur changes or keeps the driving intention in track; Step b, if judge that driving intention keeps track, then pilot model utilizes PD controlling calculation steering wheel angle knots modification according to the described driving-environment information of vehicle and status information, and calculates according to current vehicle speed and the expectation longitudinal acceleration determined by the expected elapsed time (safety time) of vehicle and front truck and export accelerator open degree value; Step c, if judge driving intention Shi Huan road, then pilot model utilizes PD to control to obtain steering wheel angle knots modification according to the described driving-environment information of vehicle and status information, and according to the present speed of vehicle and the expectation longitudinal acceleration determined by lateral acceleration, calculate and export accelerator open degree value; Steps d, compares the steering wheel angle of step b or c and accelerator open degree data to the corresponding control data being obtained true chaufeur by term vehicle internal sensors, judges whether chaufeur is interfered; Step e, repeats step a-d, until stop.
Described method also comprises: before step a, onboard exterior sensors and term vehicle internal sensors is connected with computing machine, debugging onboard exterior sensors and term vehicle internal sensors, initialization pilot model.
Judge the time window of the criterion employing 1s whether chaufeur is interfered, the renewal amount of 0.25s carries out data processing, wherein, judge that the accumulated deficiency of the data of criterion utilization orientation dish corner, accelerator open degree value and true chaufeur that whether chaufeur is interfered in 1s is as the feature of classifying, wherein, discriminant function that whether chaufeur is interfered is judged to be kernel function is the SVMs (SVM) of Gaussian function.
The characteristic of division of above-mentioned calculating is inputed to supporting vector machine model, if the result of model is greater than 0, then can judge that chaufeur is interfered, otherwise, be not interfered.
Pilot model of the present invention is based upon in existing queuing network cognition system, and while tracking expected trajectory, it can the driving performance of simulating realistic chaufeur and physiology limitation exactly, can embody the driving behavior of experienced driver.These information are defeated by pilot model by driving-environment information that the environment sensing sensor Real-time Obtaining of outside vehicle is current in real time.The information of pilot model environmentally detecting sensor, calculates chaufeur control data in real time.Obtained the real-time control data of true chaufeur by term vehicle internal sensors, just accurately can judge whether chaufeur is interfered by the control data of the driving data and true chaufeur that compare pilot model calculating.
The invention has the advantages that: the method whether the control data detection chaufeur proposing a kind of the Simulation Control data and true chaufeur of passing through to compare in real time pilot model is interfered, this testing process itself can not produce interference to chaufeur, and hardware easily realizes, cost is low; Driving data can reflect the driving condition of chaufeur truly, whether be interfered by the difference identification chaufeur of the emulated data of pilot model and the driving data of true chaufeur, the False Rate of Interference Detection can be reduced widely, improve the accuracy rate detected, advance the degree of intelligence of DAS (Driver Assistant System).
Accompanying drawing explanation
Fig. 1 is the schematic diagram utilizing pilot model to carry out chaufeur Interference Detection.
Fig. 2 is the pilot model constructional drawing in Fig. 1.
Fig. 3 is the diagram of circuit utilizing pilot model to carry out chaufeur interference detection method.
Detailed description of the invention
Describe the method for inspection according to chaufeur disturbance state of the present invention below with reference to accompanying drawings in detail.In the present invention, in order to simplified characterization, suppose that pilot model is in identical expected trajectory with true chaufeur, certainly the present invention is not limited thereto.
Fig. 1 is the schematic diagram utilizing pilot model to carry out chaufeur Interference Detection.As shown in Figure 1, pilot model is utilized to carry out the principle of chaufeur Interference Detection as follows: (1) is by onboard exterior sensors Real-time Obtaining driving-environment information (location information in the current residing track of road type (straight line or curve), vehicle, the speed of a motor vehicle, distance, vehicle (front truck and the rear car) speed of adjacent lane and the distance with this car thereof) with the front truck in same track and rear car; (2) pilot model receives the data from onboard exterior sensors, driving behavior under the current driving environment of driving behavior real-time simulation of simulation experienced driver, and export chaufeur control data to a kinetic model to realize driving behavior closed-loop corrected emulated, from the Driving control data of pilot model output as the benchmark normal driving; (3) while carrying out step (2), by the true chaufeur of onboard sensor Real-time Obtaining to the control data of vehicle; (4) comparison module receives the control data from the pilot model control data of step (2) and the true chaufeur from step (3), just accurately can judge whether chaufeur is interfered by the control data comparing pilot model and true chaufeur.
Pilot model shown in Figure 1 is based upon in existing queuing network cognition system, and while tracking expected trajectory, it can the driving performance of simulating realistic chaufeur and physiology limitation exactly, can embody the driving behavior of experienced driver.Pilot model is described in detail referring to Fig. 2.
As shown in Figure 2, pilot model comprises path planning module, takes aim at module, prediction module, comparing module 1, comparing module 2, side direction control module, longitudinal control module etc. in advance.
On the one hand, from the driving-environment information input path planning module of onboard exterior sensors, the driving intention (change or keep track) that path planning module decision-making goes out chaufeur plans corresponding driving trace, and constantly revise according to car body position in real time, take aim at module in advance and obtain expected trajectory data according to the characteristic of taking aim in advance of the described data separate chaufeur from path planning module.
On the other hand, from the car status information (S of vehicle dynamic model
n(x, y, a
x, a
y, v
x, v
y, yaw), wherein x is car body side coordinate, and y is car body along slope coordinate, a
xlongitudinal acceleration, a
ylateral acceleration, v
xlongitudinal velocity, v
ybe side velocity, yaw is car body yaw angle) input prediction module, prediction module is according to described status information prediction of output track data.Expected trajectory data and prediction locus data all input comparing module 1, obtain lateral deviation data E(will be described below to be compared to these two track datas by comparing module 1).Side direction control module according to from comparing module 1 lateral deviation data E calculated direction dish corner knots modification Δ δ (will be described below) and it is outputted to respectively comparing module 2 and longitudinal control module.Longitudinal control module calculates final accelerator open degree value α (will be described below) and exports vehicle dynamic model to, and comparing module 2 exports final steering wheel angle δ (will be described below) according to calculating from the steering wheel angle knots modification Δ δ of side direction control module and the current steering wheel angle (will be described below) of vehicle dynamic model and exported to vehicle dynamic model.Realize the closed-loop corrected of the driving behavior of pilot model thus.
Due to the comparison/belong to prior art, in this no longer repeated description than the implementation (such as, software mode, hardware mode etc.) of the control of p-control module of sensor detection-comparison module/comparing module related to when describing Fig. 1 and Fig. 2.
Describing in detail referring to Fig. 3 utilizes pilot model to carry out the method for chaufeur Interference Detection.
Pilot model is utilized to carry out the process of chaufeur Interference Detection as follows:
In step 301 and 302, debugging onboard exterior sensors and term vehicle internal sensors, it is made normally to work, each module of initialization pilot model also ensures that each module clock is consistent, ensures that the time that true driver vehicle advances is consistent with the enabling time of each sensor and pilot model simultaneously.Each sensor and computing machine (such as, car-mounted computer) are connected, to communicate with pilot model.
In step 303, driver vehicle advances, the driving-environment information that onboard exterior sensors Real-time Obtaining is current, the status information of term vehicle internal sensors Real-time Obtaining vehicle.Certainly, each sensor may be interrupted by certain situation (such as, sensor fault, vehicle parking etc.).
In step 304 and 305, pilot model obtains the driving-environment information of vehicle according to onboard exterior sensors, by comparing the relation of current vehicle position (that is, the position in residing track) and residing lane boundary, judge the driving intention (change or keep track) of chaufeur.
According to the driving intention (change or keep track) that step 305 obtains, pilot model is according to the current driving-environment information obtained from onboard exterior sensors, carry out path planning according to drive safety criterion, and constantly revise in real time according to the location information of vehicle.The path planning obtained according to driving intention is namely as the expected trajectory of pilot model, and pilot model is followed the trail of this expected trajectory, obtains corresponding driving behavior benchmark.Like this, the expected trajectory obtained by path planning can guarantee that pilot model is in identical or roughly the same expected trajectory with true chaufeur.
According to the driving intention that step 305 obtains, pilot model selects different modes to follow the trail of the expected trajectory obtained in step 305 according to corresponding driving intention (change or keep track).
If the driving intention obtained in step 305 keeps track, then in step 306,307,308 and 309, by two cars (Ben Che and front truck thereof) the spacing d obtained by onboard exterior sensors
n, front truck speed v
hnand by car status information S that term vehicle internal sensors obtains
n(x
n, y
n, a
xn, a
yn, v
xn, v
yn, yaw
n) send pilot model to.Pilot model take aim at the path planning that module obtained by step 305 in advance, obtain currently taking aim at time (T in advance
p=1.5s) in expected trajectory point P
n(x
n, y
n), prediction module obtains car status information S by term vehicle internal sensors
n(x
n, y
n, a
xn, a
vn, v
xn, v
vn, yaw
n) and time T is taken aim in prediction in advance
pthe position coordinate that interior vehicle will arrive
just can obtain the lateral position error E of expected trajectory and prediction locus thus
n.In order to accurately follow the trail of expected trajectory, lateral position deviation will be reduced by adjustment direction dish corner.In pilot model, utilize PD to control to obtain steering wheel angle knots modification.In longitudinal, in order to ensure the safety of driving, prevent rear-end collision from occurring, two following distances in safe range (or being greater than safety time) be ensured.For this reason, the interval time t of two cars is calculated
cn, expect longitudinal acceleration a
xnthen with the interval time t of two cars
cnwith safety time t
f(t
f=4s) the proportional relation of difference, obtain expecting longitudinal acceleration and accelerator open degree corresponding to present speed (accelerate on the occasion of representative, negative value represents brake) according to the relation of vehicle dynamics thus, formula is as follows:
Δδ
n＝k
p·a
yn+k
d·a′
yn （4）
δ
n=δ
n-1+Δδ
n （5）
By formula (1), the lateral position deviation E of the n-th step
nthe side direction coordinate of expected trajectory point is deducted by the side direction coordinate of prediction locus point.By formula (2), obtain the n-th step side velocity v according to term vehicle internal sensors
vn, calculate the lateral acceleration a arriving desired location
yn.By formula (3), the derivative a ' of the n-th step lateral acceleration can be obtained divided by the time of taking aim in advance by the difference of the n-th step lateral acceleration and the (n-1)th step lateral acceleration
yn.By formula (4), controlled by PD, obtain the n-th step steering wheel angle knots modification Δ δ
n.By formula (5), the steering wheel angle of the (n-1)th step adds steering wheel angle knots modification Δ δ
njust can obtain final steering wheel angle δ
n.In the longitudinal controling parameters of calculating (i.e. throttle or brake aperture), calculated the interval time t of the n-th step two car by formula (6)
cn, obtained expecting longitudinal acceleration by formula (7)
the last question blank provided by formula (8) obtains final accelerator open degree value α
n, wherein f (v
xn, a
d xn) be kinetic function expression formula about vehicle motor, the accelerator open degree that different longitudinal accelerations is corresponding different with longitudinal velocity.
Owing to how to realize PD control to belong to prior art, no longer describe at this.
Find out from description above, pilot model knows expected trajectory according to onboard exterior sensors, obtains control command, then export to vehicle dynamic model by the driving performance of emulation experienced driver in normal driving situation.
If the driving intention Shi Huan road obtained in step 305, then in step 310,311,312 and 313, by the driving-environment information of the adjacent lane obtained by onboard exterior sensors and the car status information S that obtained by term vehicle internal sensors
n(x
n, y
n, a
xn, a
vn, v
xn, v
vn, yaw
n) send pilot model to.The method of calculating taking aim at module, prediction module and steering wheel angle in advance in pilot model and step 306,307,308 identical with 309, difference is in longitudinal acceleration.In order to the physiology of simulating realistic chaufeur limits to, when changing, the longitudinal acceleration expected determines according to lateral acceleration, (accelerates on the occasion of representative according to the accelerator open degree that the relation of vehicle dynamics obtains expectation longitudinal acceleration corresponding, negative value represents brake), formula is as follows:
a
d xn=K·a
yn+a
d （9）
α
n=f(v
xn,a
d xn) （10）
The steering wheel angle followed the trail of required for expected trajectory is calculated by formula (1)-(5) above.By the longitudinal acceleration of formula (9) calculation expectation, wherein a
ynthe lateral acceleration that formula (2) calculates, K, a
dit is constant.Accelerator open degree value under the question blank provided by formula (10) calculates present speed and expects longitudinal acceleration.
Pilot model can be obtained by step 306-309 or step 310-313 and emulate the driving behavior data M(δ in normal driving situation (such as, keep track or change)
mn, α
mn), obtain the real-time control data D(δ of true chaufeur by term vehicle internal sensors
dn, α
dn), then judge whether chaufeur is subject to the interference of other tasks, shown in the following formula of its decision criteria by comparison module (see Fig. 1):
In this decision criteria, adopt the time window of 1s, the renewal amount of 0.25s.By formula (11), (12) steering wheel angle of pilot model is calculated respectively, the data of accelerator open degree value and the true chaufeur accumulated deficiency in 1s is as the feature of classifying, utilize gaussian kernel function certificate, by formula (11), (12) eigenwert calculated is input in SVMs function (SVM), according to result of calculation, if output valve is greater than 0 namely can judge that impact (step 314) that whether chaufeur be interfered (namely, the characteristic of division of above-mentioned calculating is inputed to supporting vector machine model, if the result of model is greater than 0, then can judge that chaufeur is interfered, otherwise, be not interfered).
Onboard exterior sensors and term vehicle internal sensors Real-time Obtaining driving-environment information and vehicle interior status information, constantly send information to pilot model, namely repeat above-mentioned step 304-315 always, until stop.
Claims (7)
1. utilize pilot model to detect a method for chaufeur disturbance state, described method comprises:
Step a, being obtained the driving-environment information of vehicle, by comparing the relation of current vehicle position and residing lane boundary, judging that chaufeur changes or keeps the driving intention in track by onboard exterior sensors;
Step b, if driving intention keeps track, then pilot model utilizes PD controlling calculation steering wheel angle knots modification according to the described driving-environment information of vehicle and status information, and calculates according to current vehicle speed and the expectation longitudinal acceleration determined by the interval time of vehicle and front truck and export accelerator open degree value;
Step c, if driving intention Shi Huan road, then pilot model utilizes PD controlling calculation steering wheel angle knots modification according to the described driving-environment information of vehicle and status information, and calculates according to the present speed of vehicle and the expectation longitudinal acceleration that calculated by lateral acceleration and export accelerator open degree value;
Steps d, compares the steering wheel angle knots modification of step b or c and accelerator open degree value with the control data being obtained true chaufeur by term vehicle internal sensors, judges whether chaufeur is interfered;
Step e, repeats step a-d, until stop,
Wherein, pilot model comprises:
Path planning module, receives the driving-environment information from onboard exterior sensors, and decision-making chaufeur changes or keeps the driving intention in track, plans corresponding driving trace, and constantly revises according to car body position in real time;
Take aim at module in advance, the characteristic of taking aim in advance according to the described data separate chaufeur from path planning module obtains expected trajectory data;
Prediction module, according to car status information computational prediction track data;
First comparing module, receives expected trajectory data and prediction locus data, and obtains lateral deviation data by the comparison of these two track datas;
Side direction control module, outputs to the second comparing module and longitudinal control module respectively according to described lateral deviation direction data calculation dish corner knots modification and lateral acceleration by it;
Longitudinal control module, according to expecting that the speed of longitudinal acceleration and current automobile calculates accelerator open degree value and exports vehicle dynamic model to;
Second comparing module, according to the current steering wheel angle of described steering wheel angle knots modification and vehicle dynamic model, calculates final steering wheel angle and exports vehicle dynamic model to, realizing the closed-loop corrected of pilot model driving behavior thus.
2. method according to claim 1, described method also comprises: before step a, onboard exterior sensors and term vehicle internal sensors is connected with computing machine, debugging onboard exterior sensors and term vehicle internal sensors, initialization pilot model.
3. method according to claim 2, wherein, computing machine is car-mounted computer.
4. method according to claim 1, wherein, according to step a, pilot model carries out path planning according to drive safety criterion, to obtain expected trajectory.
5. method according to claim 1, wherein, described driving-environment information comprises two following distances, front vehicle speed, and described status information is obtained by term vehicle internal sensors,
Wherein, the current expected trajectory point taken aim in advance in the time compares with the position coordinate that vehicle will arrive by pilot model, to obtain the lateral position error of expected trajectory and prediction locus, with calculated direction dish corner knots modification.
6. method according to claim 1, wherein, judges the time window of the criterion employing 1s whether chaufeur is interfered, the renewal amount of 0.25s,
Wherein, judge criterion that whether chaufeur is interfered be utilize model to obtain steering wheel angle, accelerator open degree value and true chaufeur the accumulated deficiency of corresponding control data in 1s as the feature of classifying,
Wherein, judge that the function whether chaufeur is interfered is the SVMs (SVM) utilizing kernel function to be Gaussian function.
7. method according to claim 6, wherein, by the characteristic of division of above-mentioned calculating input supporting vector machine model, if the result of model is greater than 0, then can judge that chaufeur is interfered, otherwise, be not interfered.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210333693.7A CN102795225B (en) | 2012-09-10 | 2012-09-10 | Method for detecting disturbance state of driver by utilizing driver-side longitudinal control model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210333693.7A CN102795225B (en) | 2012-09-10 | 2012-09-10 | Method for detecting disturbance state of driver by utilizing driver-side longitudinal control model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102795225A CN102795225A (en) | 2012-11-28 |
| CN102795225B true CN102795225B (en) | 2015-01-21 |
Family
ID=47194596
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210333693.7A Expired - Fee Related CN102795225B (en) | 2012-09-10 | 2012-09-10 | Method for detecting disturbance state of driver by utilizing driver-side longitudinal control model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102795225B (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103085815A (en) * | 2013-01-17 | 2013-05-08 | 北京理工大学 | Method for recognizing lane changing intention of driver |
| CN103600745B (en) * | 2013-11-19 | 2016-06-22 | 四川长虹电器股份有限公司 | A kind of navigation safety system for preventing fatigue driving |
| CN103818327B (en) * | 2013-11-22 | 2016-01-06 | 深圳先进技术研究院 | A kind of method and apparatus analyzing driving behavior |
| CN104260725B (en) * | 2014-09-23 | 2016-09-14 | 北京理工大学 | A kind of intelligent driving system containing pilot model |
| CN104494600B (en) * | 2014-12-16 | 2016-11-02 | 电子科技大学 | A kind of Driver intention recognition method based on SVM algorithm |
| CN106205271B (en) * | 2016-07-08 | 2018-12-11 | 成都合纵连横数字科技有限公司 | A kind of simulation system and method for the interference of driving procedure mobile phone |
| CN106371439B (en) * | 2016-09-13 | 2020-11-20 | 同济大学 | Unified automatic driving transverse planning method and system |
| CN106777747A (en) * | 2016-12-29 | 2017-05-31 | 广西航程威特科技有限公司 | A kind of three-dimensional traffic analogue simulation system |
| CN106971194B (en) * | 2017-02-16 | 2021-02-12 | 江苏大学 | Driving intention recognition method based on improved HMM and SVM double-layer algorithm |
| CN107264531B (en) * | 2017-06-08 | 2019-07-12 | 中南大学 | The autonomous lane-change of intelligent vehicle is overtaken other vehicles motion planning method in a kind of semi-structure environment |
| CN109421702A (en) * | 2017-08-25 | 2019-03-05 | 上海汽车集团股份有限公司 | A kind of automobile control method and device |
| CN108646732A (en) * | 2018-04-20 | 2018-10-12 | 华东交通大学 | The track of vehicle prediction technique being intended to, apparatus and system are manipulated based on driver |
| CN108734303A (en) * | 2018-05-29 | 2018-11-02 | 深圳市易成自动驾驶技术有限公司 | Vehicle drive data predication method, equipment and computer readable storage medium |
| CN108791301B (en) * | 2018-05-31 | 2020-03-24 | 重庆大学 | Intelligent automobile driving process transverse dynamic control method based on driver characteristics |
| CN110967991B (en) * | 2018-09-30 | 2023-05-26 | 百度（美国）有限责任公司 | Method and device for determining vehicle control parameters, vehicle-mounted controller and unmanned vehicle |
| CN111661060B (en) * | 2019-03-05 | 2022-06-21 | 阿里巴巴集团控股有限公司 | Method and device for establishing vehicle longitudinal motion model and computer system |
| KR102554023B1 (en) * | 2019-03-11 | 2023-07-12 | 현대모비스 주식회사 | Apparatus for controlling lane change of vehicle and method thereof |
| CN110155059B (en) * | 2019-06-04 | 2020-08-07 | 吉林大学 | Curve optimization control method and system |
| JP2021028795A (en) * | 2019-08-09 | 2021-02-25 | トヨタ自動車株式会社 | Proposal method and proposal system |
| CN110569783B (en) * | 2019-09-05 | 2022-03-25 | 吉林大学 | Method and system for identifying lane changing intention of driver |
| CN112863245B (en) * | 2019-11-28 | 2022-07-05 | 南京理工大学 | Vehicle track change real-time prediction method based on deep neural network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101093396A (en) * | 2007-07-04 | 2007-12-26 | 华南农业大学 | Navigation control method for agricultural machinery |
| CN101734252A (en) * | 2009-12-23 | 2010-06-16 | 合肥工业大学 | Preview tracking control unit for intelligent vehicle vision navigation |
| CN102060018A (en) * | 2009-11-18 | 2011-05-18 | 德国曼商用车辆股份公司 | Lane guidance method for a vehicle, in particular for a commercial vehicle and lane guidance system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008269357A (en) * | 2007-04-20 | 2008-11-06 | Toyota Motor Corp | Driving support device for vehicle |
-
2012
- 2012-09-10 CN CN201210333693.7A patent/CN102795225B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101093396A (en) * | 2007-07-04 | 2007-12-26 | 华南农业大学 | Navigation control method for agricultural machinery |
| CN102060018A (en) * | 2009-11-18 | 2011-05-18 | 德国曼商用车辆股份公司 | Lane guidance method for a vehicle, in particular for a commercial vehicle and lane guidance system |
| CN101734252A (en) * | 2009-12-23 | 2010-06-16 | 合肥工业大学 | Preview tracking control unit for intelligent vehicle vision navigation |
Non-Patent Citations (1)
| Title |
|---|
| JP特开2008-269357A 2008.11.06 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102795225A (en) | 2012-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102795225B (en) | Method for detecting disturbance state of driver by utilizing driver-side longitudinal control model | |
| CN111845766B (en) | Method for automatically controlling a motor vehicle | |
| CN105966396B (en) | A kind of vehicle intelligent collision control method based on driver's collision avoidance behavior | |
| CN101837781B (en) | Model based predictive control for automated lane centering/changing control systems | |
| US11643080B2 (en) | Trailing vehicle positioning system based on detected pressure zones | |
| CN109131312B (en) | ACC/ESC integrated control system and method for intelligent electric vehicle | |
| US8849515B2 (en) | Steering assist in driver initiated collision avoidance maneuver | |
| US8924079B2 (en) | Systems and methods for scheduling driver interface tasks based on driver workload | |
| CN107808027A (en) | It is adaptive with car algorithm based on improved model PREDICTIVE CONTROL | |
| CN113386795A (en) | Intelligent decision-making and local track planning method for automatic driving vehicle and decision-making system thereof | |
| US11572068B2 (en) | Trailing vehicle positioning system based on detected lead vehicle | |
| CN104709283A (en) | Lane change control apparatus and control method of the same | |
| CN111775949A (en) | Personalized driver steering behavior assisting method of man-machine driving-sharing control system | |
| CN112406820B (en) | Multi-lane enhanced automatic emergency braking system control method | |
| CN108447308A (en) | A kind of intersection vehicles risk of collision prediction technique and system based on bus or train route collaboration | |
| CN103754221A (en) | Vehicle adaptive cruise control system | |
| Zhang et al. | Data-driven based cruise control of connected and automated vehicles under cyber-physical system framework | |
| CN103927895A (en) | Vehicle curve passing through auxiliary system based on vehicle-road/vehicle-vehicle communication | |
| CN112937551B (en) | Vehicle control method and system considering input characteristics of driver | |
| Koga et al. | Realization of different driving characteristics for autonomous vehicle by using model predictive control | |
| Hima et al. | Controller design for trajectory tracking of autonomous passenger vehicles | |
| Guo et al. | Regional path moving horizon tracking controller design for autonomous ground vehicles | |
| Rath et al. | A lane keeping assist design: Adaptation to driving style based on aggressiveness | |
| Sumer et al. | Adaptive road-following preview control using radius of curvature data | |
| US11794777B1 (en) | Systems and methods for estimating heading and yaw rate for automated driving |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150121 Termination date: 20170910 |