CN109858359A - A kind of motorist driving intention discrimination method considering emotion - Google Patents
A kind of motorist driving intention discrimination method considering emotion Download PDFInfo
- Publication number
- CN109858359A CN109858359A CN201811618335.4A CN201811618335A CN109858359A CN 109858359 A CN109858359 A CN 109858359A CN 201811618335 A CN201811618335 A CN 201811618335A CN 109858359 A CN109858359 A CN 109858359A
- Authority
- CN
- China
- Prior art keywords
- emotion
- driving intention
- driving
- vehicle
- driver
- 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
- 230000008451 emotion Effects 0.000 title claims abstract description 69
- 238000012850 discrimination method Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 22
- 230000008569 process Effects 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 7
- 208000019901 Anxiety disease Diseases 0.000 claims description 4
- 230000036506 anxiety Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000002474 experimental method Methods 0.000 description 7
- 230000006698 induction Effects 0.000 description 6
- 239000000463 material Substances 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000001939 inductive effect Effects 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008921 facial expression Effects 0.000 description 2
- 230000035479 physiological effects, processes and functions Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 238000010181 skin prick test Methods 0.000 description 1
Landscapes
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention belongs to Vehicular intelligents to drive and active safety technologies field more particularly to a kind of motorist driving intention discrimination method for considering emotion.This method comprises: obtaining the related travelling characteristic in vehicle travel process, related travelling characteristic includes the vehicle marshalling situation under driving emotion of the driver in driving procedure and the driving emotion；Obtain multiple related travelling characteristics and driving intention corresponding to each related travelling characteristic, all related travelling characteristics and driving intention corresponding to related travelling characteristic are input in the supporting vector machine model pre-established and are trained, model parameter is obtained；It is used to judge the driving intention in each driver's driving vehicle using the supporting vector machine model of model parameter after training.This method, by accurate recognition driver's driving intention, improves the safety of vehicle driving under conditions of considering emotion.
Description
Technical field
It drives the invention belongs to Vehicular intelligent and is driven with active safety technologies field more particularly to a kind of automobile for considering emotion
Sail people's driving intention discrimination method.
Background technique
With China's rapid economic development, private car owning amount is risen year by year, Human Automobile Environment in road traffic system
It is particularly thorny, wherein caused traffic accident accounts for 70% or more due to driver.Therefore, system, accurately perception row
The physiology of driver, psychological characteristic, carry out the research of driver's driving intention discrimination method during sailing, to reduction road traffic
The generation of accident, the level of security for improving road traffic system are of great significance to.
Currently, experts and scholars both domestic and external are it is believed that emotion is that driver stimulates things various in traffic environment
Psychoreaction is a kind of general performance of human physiology-psychology characteristic.Cognition, processing of the driver to extraneous environmental information, and its
The decision of next step behavior is influenced by affective state.
Summary of the invention
(1) technical problems to be solved
For existing technical problem, the present invention provides a kind of motorist driving intention identification for considering emotion
Method, this method, by accurate recognition driver's driving intention, improve the safety of vehicle driving under conditions of considering emotion
Property.
(2) technical solution
In order to achieve the above object, the main technical schemes that the present invention uses include:
A kind of motorist driving intention discrimination method considering emotion, includes the following steps:
The related travelling characteristic in vehicle travel process is obtained, the correlation travelling characteristic includes driver in driving procedure
In driving emotion and the driving emotion under vehicle marshalling situation；The emotion that drives is the monitoring driver according to acquisition
Image is identified and is determined that the vehicle marshalling situation is to carry out according to the image of vehicle where the monitoring driver of acquisition
It identifies and determines；
Multiple related travelling characteristics and driving intention corresponding to each related travelling characteristic are obtained, by all correlations
Travelling characteristic and driving intention corresponding to related travelling characteristic are input in the supporting vector machine model pre-established and carry out
Training obtains model parameter；
It is used to judge the driving meaning in each driver's driving vehicle using the supporting vector machine model of model parameter after training
Figure.
Further, the driving emotion is to be detected using China's PAD model emotion scale in advance and determined and determined
Justice.
Further, the driving emotion include indignation, surprised, fear, anxiety, it is helpless, despise, easily and pleasure.
Further, the vehicle marshalling situation is by vehicle place lane and adjacent lane in vehicle travel process to described
The active force of vehicle indicates.
Further, the driving intention includes driving intention relevant to speed and driving intention relevant with lane-change.
Further, the driving intention relevant to speed includes accelerating, slow down and keeping speed.
Further, the driving intention relevant to lane-change includes lane-change and straight trip.
Further, the driving intention keeps speed straight trip, accelerates straight trip, straight trip of slowing down, keep speed lane-change, accelerate
Lane-change and totally six kinds of deceleration lane-change.
(3) beneficial effect
The identification of driver's driving intention provided by the invention is for enhancing the validity of automobile active safety system and mentioning
The safety of high road traffic system is of great significance.
Detailed description of the invention
Fig. 1 is the partial visual emotion inducing materials used in the embodiment of the present invention；
Fig. 2 is the PAD project of standard development table used in the embodiment of the present invention；
Fig. 3 is the structure of support vector machines in the embodiment of the present invention；
Fig. 4 is driver's speed intention assessment model based on DAG algorithm in the embodiment of the present invention；
Fig. 5 is driver's lane-changing intention identification model based on DAG algorithm in the embodiment of the present invention.
Specific embodiment
In order to preferably explain the present invention, in order to understand, with reference to the accompanying drawing, by specific embodiment, to this hair
It is bright to be described in detail.
A kind of motorist driving intention discrimination method considering emotion, includes the following steps:
S1, the driving emotion for inducing testee (i.e. driver), and the induction result for driving emotion is detected.It adopts
The negative sense emotion and positive emotion proposed with Victor .S. Johnston, carries out emotion common in driver's driving process
Investigation and analysis, choose indignation, surprised, fear, anxiety, it is helpless, despise, easily, 8 kinds of driving emotions of pleasure.
Firstly, using integrated multi-channel emotion induce method 8 kinds of drivings emotions of testee are induced: to be tested
Examination person shows the picture that intense emotion color is had in international emotion picture system and Chinese emotion stimulus material library, and Xiang Qixiang
The scene of thin description picture or the story for being included, allow testee to have feeling on the spot in person, adopt as shown in Figure 1 for the present invention
Partial visual emotion inducing materials；The video that particular emotion is excited in Chinese emotion stimulus material library is played to measured,
The emotion that front excites further is deepened；For a long time using Virtual Driving Platform setting traffic accident, traffic congestion, intersection etc.
Squeeze road to, vehicle, interference vehicle malice hinders testee the traffic scenes such as to move ahead, excite the frightened, helpless of measured, anxiety,
Angry emotion；Building drives competition game scene and the methods of the induction of integrated use language and psychological hint excite slighing for measured
Depending on emotion；By with testee's communication exchange, give small gift, or allow its to mirror smile, sing the methods of excitation it is light, pleased
Happy emotion；Using some strange news and intriguing stories, out of the knowledge of common sense, the world record etc. that data are exaggerated very much is played or is showed
Subject, and be aided with language induction, atmosphere set off by contrast with the diversification emotion exciting methods such as material reward, excite that subject's is surprised
Mood.
Secondly, the induction result for driving emotion to testee detects: 1) the comprehensive physiology using testee is believed
Number detection, utilizes PsyLAB Human Engineering system to extract the physiological datas letter such as electrocardio, breathing, pulse, skin pricktest of testee
Breath, the emotion identification method based on physiologic information proposed using Haag A, the induction for whether completing emotion to subject are made
Judgement；2) according to the behavior expression of testee, as facial expression, limb action judge whether that completing target drives emotion
It induces；3) after the end of the experiment, tissue testee watches the video of itself movement and facial expression in experimentation immediately and returns
It puts, Chinese PAD model emotion scale is filled in by testee, pleasant degree P, activity A and dominance D is calculated.By PAD tri-
Parameter value, according to the Chinese PAD model emotion scale that the Chinese Academy of Sciences revises, the induction for whether completing target emotion to driver is made
Judgement.As shown in Fig. 2, being PAD project of standard development table.
Parameter P indicates pleasure degree: P=S1-S4+S7-S10 (1)
Parameter A indicates activity: A=-S2+S5-S8+S11 (2)
Parameter D indicates dominance: D=S3-S6+S9-S12 (3)
There is the specific driver for driving emotion to carry out driving experiment by S2, selection, and the driving experiment includes virtual driving
Experiment and real vehicle drive experiment.In virtual driving experiment, the specific driver for driving emotion is inspired in driving simulator
On driven, in the process, the data acquisition module of driving simulator can directly obtain the vehicle marshalling under current state
Situation, the vehicle marshalling situation include the location information of vehicle and the motion information of vehicle, and vehicle movement information includes vehicle
Velocity information (accelerate, slow down and keep speed) and vehicle lane-change information (lane-change, straight trip).
It is driven in experiment in real vehicle, is inspired the specific driver for driving emotion in actual vehicle and road environment
It is driven, vehicle marshalling situation is obtained by the velocity sensor, rangefinder, GPS etc. that are installed on vehicle.
S3, the motorist driving intention identification model for considering emotion is established using the method for support vector machines.
Firstly, determining sample class number according to the classification of driving intention.
Driving intention is divided into following 6 class: keeping speed straight trip, acceleration straight trip, straight trip of slowing down, keeps speed lane-change, adds
Quick change road and deceleration lane-change.Wherein, k=3 when identifying for the driving intention of travel speed refers to and keeps speed, accelerates and subtract
Fast 3 kinds of intentions relevant to travel speed；K=2 when identifying for the driving intention of vehicle lane-changing, that is, refer to 2 kinds of lane-change and straight trip
Intention relevant to traveling kind lane-change.
Secondly, establishing 4 two-value classifiers in the case where each drives emotion: lane-change and keep straight trip, accelerate with
Speed, acceleration and deceleration are kept, speed is kept and slows down.Process is as follows:
Classification line equation is solved, it is to solve antithesis optimization method that it is equations turned, which can will to solve classification line, as shown in Figure 3:
In formula, K (Xi,Xj) it is the kernel function for meeting Mercer condition, XiAnd XjFor sample data constitute feature vector,
By introducing relaxation factor ζi> 0, it may be determined that objective function are as follows:
In formula, c is penalty；
Determine optimal classification function:
Y (x)=sgn (ω Q (x)+b)=sgn [αiyiK(xi,xj)+b] (6)
In formula, corresponding any supporting vector, b can be determined by following formula:
yi[(ω·x)+b]≥1-ξi, i=1,2 ..., n (7)
Wherein, 0≤αi≤ c is Lagrange multiplier.
Finally, being established by DAG algorithm and training the motorist driving intention identification model for considering emotion.It will be known
Driving emotion, vehicle marshalling situation and corresponding driving intention input jointly supporting vector model carry out parameter training, obtain
Driving intention recognizes model.Wherein, it by construction feature vector Data (t) and label amount Label (t), is instructed respectively as SVM model
Practice the characteristic parameter of parameter and verifying, in which:
Data (t)={ x1(t),x2(t),...,xi(t),...,xn(t)} (8)
N is training samples number, x in formulai(t) it is chosen for corresponding eigenvector information in the t period, present embodiment
Feature vector is the driving emotion and vehicle marshalling situation of driver, wherein drives the driving of emotion in the car by installation
People's image collecting device obtains, and vehicle marshalling situation is by lane where target carriage and adjacent lane to the active force table of target carriage
Show:
Label (t)={ y (t) } (9)
Tag along sort of y (t) the expression support vector machines in each node in formula, y (t) ∈ { -1,1 }, such as in driver
Lane-change is realized in identification model, and lane-change is denoted as 1, and straight trip is denoted as -1.
Driver's driving intention identification model based on DAG algorithm is obtained, and selects height under Matab Lib-svm environment
This Radial basis kernel function imports sample with default parameters and is trained to model, establishes and considers that the motorist of emotion drives meaning
Figure discrimination method.
As shown in Figure 4,5, in present embodiment based on DAG algorithm driver's speed intention assessment model and driver
Lane-changing intention identification model.
The technical principle of the invention is described above in combination with a specific embodiment, these descriptions are intended merely to explain of the invention
Principle shall not be construed in any way as a limitation of the scope of protection of the invention.Based on explaining herein, those skilled in the art
It can associate with other specific embodiments of the invention without creative labor, these modes fall within this hair
Within bright protection scope.
Claims (8)
1. a kind of motorist driving intention discrimination method for considering emotion, which comprises the steps of:
The related travelling characteristic in vehicle travel process is obtained, the correlation travelling characteristic includes driver in driving procedure
Drive the vehicle marshalling situation under emotion and the driving emotion；The emotion that drives is the image according to the monitoring driver of acquisition
It is identified and is determined, the vehicle marshalling situation is to be identified according to the image of the monitoring driver place vehicle of acquisition
And determine；
Multiple related travelling characteristics and driving intention corresponding to each related travelling characteristic are obtained, by all related travelings
Feature and driving intention corresponding to related travelling characteristic are input in the supporting vector machine model pre-established and are trained,
Obtain model parameter；
It is used to judge the driving intention in each driver's driving vehicle using the supporting vector machine model of model parameter after training.
2. the motorist driving intention discrimination method according to claim 1 for considering emotion, which is characterized in that described
Driving emotion is in advance using China's PAD model emotion scale is detected and is determined and is defined.
3. the motorist driving intention discrimination method according to claim 1 for considering emotion, which is characterized in that described
Drive emotion include indignation, surprised, fear, anxiety, it is helpless, despise, easily and pleasure.
4. the motorist driving intention discrimination method according to claim 1 for considering emotion, which is characterized in that described
Vehicle marshalling situation includes: more than two vehicles in the image of vehicle where identifying driver, and according to preset time period
Active force where image determines driver between vehicle and adjacent lane, is expressed as vehicle marshalling state for determining active force
Gesture.
5. the motorist driving intention discrimination method according to claim 1 for considering emotion, which is characterized in that described
Driving intention includes driving intention relevant to speed and driving intention relevant with lane-change.
6. the motorist driving intention discrimination method according to claim 5 for considering emotion, which is characterized in that described
Driving intention relevant to speed includes accelerating, slow down and keeping speed.
7. the motorist driving intention discrimination method according to claim 6 for considering emotion, which is characterized in that described
Driving intention relevant to lane-change includes lane-change and straight trip.
8. the motorist driving intention discrimination method according to claim 7 for considering emotion, which is characterized in that described
Driving intention keeps speed straight trip, accelerates straight trip, straight trip of slowing down, keep speed lane-change, accelerate lane-change and totally six kinds of deceleration lane-change.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811618335.4A CN109858359A (en) | 2018-12-28 | 2018-12-28 | A kind of motorist driving intention discrimination method considering emotion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811618335.4A CN109858359A (en) | 2018-12-28 | 2018-12-28 | A kind of motorist driving intention discrimination method considering emotion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109858359A true CN109858359A (en) | 2019-06-07 |
Family
ID=66892888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811618335.4A Pending CN109858359A (en) | 2018-12-28 | 2018-12-28 | A kind of motorist driving intention discrimination method considering emotion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109858359A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110569783A (en) * | 2019-09-05 | 2019-12-13 | 吉林大学 | Method and system for identifying lane changing intention of driver |
| CN112434588A (en) * | 2020-11-18 | 2021-03-02 | 青岛慧拓智能机器有限公司 | Inference method for end-to-end driver expressway lane change intention |
| CN113204920A (en) * | 2021-05-12 | 2021-08-03 | 紫清智行科技(北京)有限公司 | Intelligent vehicle lane change comfort evaluation and track planning method and device based on support vector machine |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201881988U (en) * | 2010-09-17 | 2011-06-29 | 长安大学 | Vehicle lane changing auxiliary device |
| CN103077603A (en) * | 2012-06-06 | 2013-05-01 | 王晓原 | Identification system for free flow car driving tendency based on dynamic collaborative deduction of people and vehicle environment |
| CN104260723A (en) * | 2014-09-29 | 2015-01-07 | 长安大学 | Device and method for predicting motion state of vehicle behind by tracing |
| CN107223101A (en) * | 2016-06-23 | 2017-09-29 | 驭势科技（北京）有限公司 | Vehicular automatic driving method and Vehicular automatic driving system |
| CN107341468A (en) * | 2017-06-30 | 2017-11-10 | 北京七鑫易维信息技术有限公司 | Driver status recognition methods, device, storage medium and processor |
| CN108995654A (en) * | 2018-07-06 | 2018-12-14 | 北京理工大学 | A kind of driver status recognition methods and system |
-
2018
- 2018-12-28 CN CN201811618335.4A patent/CN109858359A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201881988U (en) * | 2010-09-17 | 2011-06-29 | 长安大学 | Vehicle lane changing auxiliary device |
| CN103077603A (en) * | 2012-06-06 | 2013-05-01 | 王晓原 | Identification system for free flow car driving tendency based on dynamic collaborative deduction of people and vehicle environment |
| CN104260723A (en) * | 2014-09-29 | 2015-01-07 | 长安大学 | Device and method for predicting motion state of vehicle behind by tracing |
| CN107223101A (en) * | 2016-06-23 | 2017-09-29 | 驭势科技（北京）有限公司 | Vehicular automatic driving method and Vehicular automatic driving system |
| CN107341468A (en) * | 2017-06-30 | 2017-11-10 | 北京七鑫易维信息技术有限公司 | Driver status recognition methods, device, storage medium and processor |
| CN108995654A (en) * | 2018-07-06 | 2018-12-14 | 北京理工大学 | A kind of driver status recognition methods and system |
Non-Patent Citations (3)
| Title |
|---|
| 刘亚奇: "跟驰状态汽车驾驶员意图的情感影响机制及辨识方法", 《万方平台》 * |
| 张元元等: "基于驾驶模拟实验的自由流状态汽车驾驶倾向性辨识模型验证方法", 《武汉理工大学学报》 * |
| 马晶晶等: "基于C-P2D-HMM的机动车驾驶意图辨识", 《科技与企业》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110569783A (en) * | 2019-09-05 | 2019-12-13 | 吉林大学 | Method and system for identifying lane changing intention of driver |
| CN110569783B (en) * | 2019-09-05 | 2022-03-25 | 吉林大学 | Method and system for identifying lane changing intention of driver |
| CN112434588A (en) * | 2020-11-18 | 2021-03-02 | 青岛慧拓智能机器有限公司 | Inference method for end-to-end driver expressway lane change intention |
| CN113204920A (en) * | 2021-05-12 | 2021-08-03 | 紫清智行科技(北京)有限公司 | Intelligent vehicle lane change comfort evaluation and track planning method and device based on support vector machine |
| CN113204920B (en) * | 2021-05-12 | 2022-02-15 | 紫清智行科技(北京)有限公司 | Intelligent vehicle lane change comfort evaluation and track planning method and device based on support vector machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108995654B (en) | Driver state identification method and system | |
| CN109858359A (en) | A kind of motorist driving intention discrimination method considering emotion | |
| CN108394411B (en) | Vehicle follows start control device | |
| CN109242251A (en) | Vehicular behavior safety detecting method, device, equipment and storage medium | |
| CN110427850A (en) | Driver's super expressway lane-changing intention prediction technique, system, device | |
| CN112382054B (en) | Automobile driving early warning prompting system and method based on vehicle-road cooperation | |
| Liao et al. | Detection of driver cognitive distraction: A comparison study of stop-controlled intersection and speed-limited highway | |
| CN104013414B (en) | A kind of Study in Driver Fatigue State Surveillance System based on intelligent movable mobile phone | |
| US10937334B2 (en) | Information providing system | |
| Doshi et al. | Examining the impact of driving style on the predictability and responsiveness of the driver: Real-world and simulator analysis | |
| CN106985668B (en) | Vehicle control system | |
| US20160246298A1 (en) | Drive assist apparatus | |
| Schiff et al. | Perceiving and driving: Where parallel roads meet | |
| CN112070823A (en) | Video identification-based automobile intelligent cabin adjusting method, device and system | |
| CN110077398A (en) | A kind of Risk Management method for intelligent driving | |
| CN108859935A (en) | Pilotless automobile and its suggestion device and method | |
| CN105105938A (en) | Intelligent wheelchair control method and system based on face orientation identification and tracking | |
| CN105955099A (en) | Driving mode switching method and apparatus for an unmanned vehicle | |
| CN103390193B (en) | A kind of automatic trainer of rat robot towards navigation and rat behavior recognition methods and training method | |
| CN110276968A (en) | A kind of fog-zone highway super long tunnel entrance security inducible system | |
| US20200121889A1 (en) | Mental and physical state inducement apparatus, mental and physical state inducement method, and storage medium storing control program | |
| CN101941425A (en) | Intelligent recognition device and method for fatigue state of driver | |
| CN110400463A (en) | A kind of safe driving method for early warning recommended based on best travel speed | |
| Rettenmaier et al. | Modeling the interaction with automated vehicles in road bottleneck scenarios | |
| CN103247216A (en) | Teaching experiment device based on miniature intelligent vehicle |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190607 |
|
| RJ01 | Rejection of invention patent application after publication |