CN114155742A - Method for evaluating and early warning longitudinal driving risk of internet vehicle - Google Patents
Method for evaluating and early warning longitudinal driving risk of internet vehicle Download PDFInfo
- Publication number
- CN114155742A CN114155742A CN202111411639.5A CN202111411639A CN114155742A CN 114155742 A CN114155742 A CN 114155742A CN 202111411639 A CN202111411639 A CN 202111411639A CN 114155742 A CN114155742 A CN 114155742A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- risk
- driver
- indexes
- risk level
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a vehicle networking technology, in particular to a networking vehicle longitudinal driving risk assessment and early warning index and method. The method is characterized by comprising the following steps: 1) classifying the risk level of the driver based on longitudinal acceleration data in the large amount of vehicle track data; 2) screening out vehicle operation indexes and safety substitute indexes related to the risk level sensed by the driver as independent variables, and establishing a Logit model for evaluating the risk level as a risk evaluation model; 3) comparing the prediction effects of different prediction step models for each following segment, and selecting a prediction step corresponding to the optimal prediction effect; 4) and applying the established risk evaluation model to an online vehicle platform, predicting and evaluating the risk level, displaying the risk level through vehicle-mounted equipment, and early warning the vehicle. The method and the system can provide real-time prepared risk grade early warning for the driver, improve the attention of the driver and reduce the driving risk.
Description
Technical Field
The invention relates to a vehicle networking technology, in particular to a networking vehicle longitudinal driving risk assessment and early warning index and method.
Background
With the development of economy, the automobile holding capacity and the traffic volume are continuously improved, and frequent traffic accidents caused by the continuous improvement bring great threat to lives and properties of people. The early warning is provided to the safety level that the driver is located in real time before the traffic accident takes place, can promote driver's consciousness and drive concentration degree, effectively promotes traffic safety level. With the development of the car networking technology, the real-time acquisition of the running information of the car is realized, and the data can help to supervise and judge the risk level of the car.
Due to the limited application scale of the networked vehicles, no large amount of operation data of the networked vehicles can be obtained for research. Therefore, in the existing research, on one hand, the risk level of the traffic is evaluated from a macroscopic view, and accident black spots are obtained based on traffic accident data of past years, so that the management of the accident black spots is enhanced, and the traffic risk is reduced. However, this method only evaluates the traffic safety level of one area for macroscopic data including flow rate, average vehicle speed, etc., and cannot timely judge the risk level of each vehicle according to the real-time vehicle operation information. On the other hand, the study at the microscopic level is to measure the risk level of the vehicle in real time according to the safety substitute indexes proposed by the traditional manual driving of the vehicle, but the method obtains the risk level based on objective indexes, and the indexes have certain gap with the risk level subjectively felt by the driver. Therefore, a model which is more suitable for the subjective perception level of the risk of the driver needs to be established so as to better match the cognitive habits and the operation habits of the driver, and the model is further applied to a future automatic driving vehicle control strategy so that the future automatic driving vehicle control strategy is more acceptable to the driver.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a method for evaluating and early warning the longitudinal driving risk of the internet connected vehicle.
The research shows that the rapid deceleration behavior of the vehicle is directly related to the risk level of the subjective feeling of the driver. The driver can do the behavior of rapid deceleration only when considering that the environment in which the driver is located is risky. The longitudinal acceleration of the vehicle may therefore reflect the level of risk perceived by its driver and contribute to a clear awareness of the various styles of drivers of their level of risk, thereby improving vigilance for high risk conditions. Therefore, the risk level of the vehicle is judged according to the longitudinal acceleration of the vehicle in the driving process, the risk assessment prediction model is constructed, the driver is sent with reminding information to give an early warning, the accident rate is reduced, the casualties and property loss are reduced, a longitudinal driving risk assessment and early warning method is provided by combining the real-time data of the vehicle, and the risk level subjective and perceived by the driver can be effectively monitored in real time and effectively early warned.
The purpose of the invention can be realized by the following technical scheme:
a longitudinal driving risk assessment and early warning method comprises the following steps:
1) taking the longitudinal acceleration of the vehicle as an index for evaluating the risk of subjective perception of a driver, dividing a data set into a training set and a test set, and grading the risk level of the vehicle according to the longitudinal acceleration of the test set;
2) selecting an index which is obviously related to the risk level sensed by a driver as an independent variable by taking the running index of the vehicle and a plurality of safety substitution indexes as alternatives, and establishing a Logit model for evaluating the risk level;
3) considering that the reaction time of the driver has certain influence on the prediction result of the model, different values are taken as different prediction step lengths in the range, wherein the prediction step length with the best prediction result, namely the optimal prediction step length, can be regarded as the reaction time of the driver;
3) the established risk assessment model is applied to the internet vehicles capable of acquiring vehicle motion information in real time, the risk level of the internet vehicles is predicted and assessed, the risk level of the internet vehicles is judged, and the information is sent to the vehicles to warn the drivers.
The step 1) is specifically as follows: the vehicle adopting a certain deceleration is considered to be the reaction of the driver to the risky environment in which the driver is positioned, and the longitudinal acceleration of the vehicle is selected as an index for evaluating the subjective perception risk of the driver. When the driver takes emergency braking and the acceleration is less than a certain threshold value, the risk level is 1, namely, the driver is in an unsafe state; the remaining states are safe states with a risk level of 0.
The step 2) specifically comprises the following steps:
21) selecting the operation indexes of the vehicle and the widely used safety substitute indexes as alternatives, wherein the operation indexes of the vehicle comprise: the speed of the vehicle, the speed of the front vehicle, the speed difference of the two vehicles, the distance between the two vehicles, the acceleration of the front vehicle and the like; common widely-used Safety indexes include Distance Headway (DHW), Distance Headway (THW), Time To Collision (TTC), accident Deceleration to avoidance (DRAC), Safety threshold (SM), and the like, which can reflect objective risk level of a vehicle from different angles.
22) Analyzing the correlation among different indexes, and selecting the index with low correlation level and no multiple collinearity as an independent variable;
23) constructing a Logit model by taking the risk level of the vehicle judged by the acceleration as a dependent variable;
24) considering that the reaction time of the driver is 0.5-2s, different values are taken as different prediction steps in this range, wherein the prediction step having the best prediction result, i.e., the optimal prediction step, can be regarded as the reaction time of the driver.
In step 21), the safety substitute index may be selected from a plurality of indexes including, but not limited to, the safety index, which are evaluated from the perspective of objective indexes for the risk level, and it is determined whether the indexes can reflect the risk level that the driver subjectively perceives.
In the step 22), the correlation of the candidate independent variable indexes needs to be calculated, and indexes with too high correlation or multiple collinearity are excluded. Here they are screened by computing Spearman correlation coefficients and coefficient of Variance Inflections (VIF) between the candidate arguments:
1) the Spearman correlation coefficient rho between every two safety substitution indexes serving as independent variables is less than 0.5, and when the correlation coefficient between the two variables is large, one of the two variables needs to be deleted;
2) the coefficient of variance expansion can calculate the multiple collinearity severity of the independent variables in the measurement model, and the independent variables with the coefficient of variance expansion smaller than 5 are screened out.
In the step 23), a Logit model is constructed in consideration of different risk levels, wherein a linear relation between a logarithmic probability Logit (Y) of a dependent variable Y and an independent variable X is as follows:
wherein p isjIs the probability that the vehicle is at a level of risk of j.
The method creatively selects the dependent variable and the independent variable, and adopts the Logit classical model to solve.
Compared with the prior art, the method and the device have the advantages that on the basis of the prior art, the risk level which is subjectively perceived by the driver is represented according to the operation of the driver in the actual vehicle track, and the risk level of the driver is judged according to the longitudinal acceleration. And subjective risk level of the vehicle is evaluated according to real-time motion information and common objective safety indexes of different vehicles, so that real-time prepared risk level early warning is provided for a driver, attention of the driver is improved, and driving risk is reduced.
The invention can solve the problems of low early warning efficiency and the like depending on static data or macroscopic traffic flow data and depending on years of historical accident data at present, can obtain the risk level of the longitudinal acceleration of the vehicle by utilizing the real-time vehicle motion information under the vehicle networking environment, and can realize real-time early warning on the driver, thereby effectively improving the perception capability of the driver on the potential risk before the accident occurs. In addition, the risk level is described by the acceleration and deceleration behaviors of the driver, the established model is more in line with the subjective perception level of the driver on the risk, the model is more in line with the cognition and operation habits of the driver, and the model can be further applied to a future automatic driving vehicle control strategy to enable the model to be more easily accepted by the driver.
Drawings
FIG. 1 is a flow diagram of an embodiment of the present invention.
Fig. 2 is a data processing flow chart.
FIG. 3 is an example argument correlation coefficient.
FIG. 4 shows the evaluation results of the example model.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Examples
As shown in fig. 1, a method for evaluating and warning the longitudinal driving risk of an internet vehicle includes the following steps: firstly, according to the vehicle track information of the public vehicle track data set NGSIM data set, 80% is selected as a training set, and 20% is selected as a testing set. And taking the longitudinal acceleration of the vehicle as an index for evaluating the risk, and carrying out risk grade division according to the longitudinal acceleration data of the training set. And taking the running indexes and a plurality of safety substitution indexes of the vehicle as candidate independent variables, selecting indexes which are obviously related to the risk level of the subjective perception of the driver as the independent variables, and establishing a Logit model for evaluating the risk level. In addition, the influence of the reaction time of the driver is also considered, different prediction step lengths are selected according to the reaction time of the driver, and the optimal prediction step length of the longitudinal driving risk assessment model is obtained and is the reaction time of the driver. The established risk assessment model is applied to the internet vehicles capable of acquiring vehicle motion information in real time, the risk levels of the internet vehicles are predicted and assessed, the risk levels of the internet vehicles are judged, the risk levels are sent to the vehicles to warn drivers, and therefore real-time monitoring and effective early warning are conducted on vehicle risks.
The algorithm is embodied as follows:
1) taking the NGSIM data set as an example, the following segments (the screening indexes are that the following distance is less than 150m and the following vehicle distance is less than 8s) of the car following the car and located in the same lane are screened, so as to ensure that the state of the following car is influenced by the front car.
And taking the longitudinal acceleration of the vehicle as an index for evaluating the risk when the vehicle decelerates suddenly. Namely the longitudinal acceleration a is less than or equal to-3 m/s2Then it is considered as unsafe state with a risk level of 1; otherwise it is in a safe state with a risk level of 0. Screening vehicles with rapid deceleration behaviors, and extracting a rapid deceleration process and data of 5 seconds before and after the rapid deceleration process, thereby extracting 35 vehicle-following segments. Thereafter, 28 segments of the data set were used as training sets and the remaining 4 segments were used as test sets.
2) Selecting the operation indexes of the vehicle and the widely used safety substitute indexes as alternatives, wherein the operation indexes of the vehicle comprise: the speed of the vehicle, the speed of the front vehicle, the speed difference of the two vehicles, the distance between the two vehicles, the acceleration of the front vehicle and the like; the safety surrogate indicators include: distance Headway (DHW), Distance Headway (THW), Time To Collision (TTC), accident avoidance Deceleration (DRAC), Safety threshold (SM). Judging the correlation and multiple collinearity of the candidate independent variables:
(1) the Spearman correlation coefficient is calculated to obtain the correlation coefficient of each independent variable factor (for example, fig. 3), and factors highly correlated with the rest of the variables are deleted.
Through calculating the correlation coefficient, the high correlation of the speeds of the front and rear vehicles and the high correlation of a plurality of safety substitute indexes are found, and the follow-up important consideration is needed.
(2) Calculating the severity of multiple collinearity in a variance expansion factor (VIF) measurement model, and screening independent variables with the VIF larger than 5. Examples are shown in Table 1:
TABLE 1 independent variable VIF value
All independent variable features have VIF coefficient values less than 5. Combining the calculation results of the correlation coefficients, the finally selected independent variables are as follows: independent variables such as front vehicle acceleration, the square of the difference between the front vehicle speed and the rear vehicle speed, the front-rear vehicle distance, THW, TTC and the like.
(3) After the independent variable is determined, when a Logit model is constructed, the change of the reaction time of a driver in the range of 0.5-2s is considered, values are respectively taken as prediction step lengths in the interval of 0.1s, and the value with the best prediction effect is taken as the reaction time of the driver. Table 2 and fig. 4 are example results.
Table 2 shows the results
(4) Partial results (8 segments) of the Logit model for assessing risk ratings were established for 28 following segments of the training set as shown in table 3:
table 3 example of Logit model parameter values and reaction time results
It can be seen that the independent variables selected in different following segments are different, for example, the distance between the front vehicle and the rear vehicle appears 7 times in table 3; THW occurred 5 times; TTC occurred 7 times. The final model argument retention principle is: if the occurrence frequency is more than 50%, the independent variable is retained.
The results of 28 following segments are counted, the value of each parameter is averaged, the independent variable and the coefficient thereof as well as the average reaction time of the driver can be determined, and the results are shown in table 4:
TABLE 4 Final Logit model independent variable coefficient value and average driver response time
And verifying the test set according to the model to obtain the accuracy of 61%.
4) And sending the risk level of the vehicle to warn a driver.
And calculating the risk level of the driver and sending the risk level to the driver by considering the response time of the vehicle, so that the prediction and early warning of the risk level are realized, the driver can clearly know the safety risk level of the driver, the alertness is improved, and the safety level is improved.
Claims (5)
1. A method for evaluating and early warning the longitudinal driving risk of an internet connected vehicle is characterized by comprising the following steps:
1) the subjective perception of the driver on the risk level triggers the action reaction of the driver, which is expressed as the longitudinal acceleration of the vehicle; the longitudinal acceleration of the vehicle can be used for reflecting the judgment of the risk level of the driver, and the risk level of the driver is classified based on the longitudinal acceleration data in a large amount of vehicle track data;
2) screening out vehicle operation indexes and safety substitution indexes related to the risk level sensed by the driver as independent variables, and establishing a Logit model for evaluating the risk level as a risk evaluation model, wherein the indexes comprise the vehicle operation indexes and the safety substitution indexes;
the vehicle operation index includes: the speed of the vehicle, the speed of the front vehicle, the speed difference of the two vehicles, the distance between the two vehicles and the acceleration of the front vehicle;
the safety surrogate indicators include: time-to-collision (TTC), headway (THW), accident-avoidance Deceleration (DRAC), Safety threshold (SM);
3) comparing the prediction effects of different prediction step models for each following segment, and selecting the prediction step corresponding to the optimal prediction effect as the optimal prediction duration of the longitudinal driving risk assessment model, namely the response time of the driver;
4) the established risk assessment model is applied to an internet vehicle platform capable of acquiring vehicle motion information in real time, risk levels are predicted and assessed, the risk levels are displayed through vehicle-mounted equipment, and early warning is carried out on vehicles.
2. The method according to claim 1, wherein the step 1) is specifically: selecting the longitudinal acceleration of the vehicle as an index for evaluating the risk, and when the vehicle adopts emergency braking, namely the acceleration is less than a certain threshold value, the risk level is 1, namely the vehicle is in an unsafe state; the remaining states are safe states with a risk level of 0.
3. The method according to claim 1, wherein the step 2) comprises the following steps:
21) selecting the operation indexes of the vehicle and the widely used safety substitute indexes as alternatives, wherein the operation indexes of the vehicle comprise: the speed of the vehicle, the speed of the front vehicle, the speed difference of the two vehicles, the distance between the two vehicles and the acceleration of the front vehicle; common widely-used Safety indexes include Distance Headway (DHW), Distance Headway (THW), Time To Collision (TTC), accident-avoidance Deceleration (DRAC), Safety threshold (SM), and other indexes, which can reflect the Safety level of an objective angle from different angles;
22) the risk level sensed by a driver is judged as a dependent variable according to the longitudinal acceleration of the vehicle, and indexes which are screened from alternative variables and are obviously related to the risk level are used as independent variables to construct a Logit model;
23) considering that the reaction time of the driver is 0.5-2s, setting different prediction step lengths at intervals of 0.1s in the range to construct a Logit model prediction risk level, wherein the prediction step length corresponding to the best prediction result is the optimal prediction step length, namely the reaction time of the driver;
24) dividing a data set into a training set and a testing set according to the proportion of 8: 2;
25) each following segment can construct a corresponding Logit model, wherein the corresponding Logit model comprises an independent variable corresponding to the Logit model;
observing the independent variables determined by all the following segments in the training set, counting the frequency of each independent variable appearing in all the following segments, and selecting the independent variable as one independent variable in the final model when the frequency of appearance exceeds 50%; and the method for confirming the coefficient of each independent variable in the final model is the coefficient mean value of all the appeared independent variables, the final model is obtained according to the training set, the data of the test set is used for testing, and the prediction result is evaluated.
4. The method of claim 3, wherein the independent variable screening comprises: said step 22), the alternative is neededIndependent variableCalculating the correlation of the indexes, and eliminating indexes with over-high correlation or multiple collinearity;
they were screened with Spearman correlation coefficient and coefficient of Variance Inflationation Factor (VIF):
1) the Spearman correlation coefficient rho between every two safety substitution indexes serving as independent variables is less than 0.5, and when the correlation coefficient between the two variables is large, one of the two variables needs to be deleted;
wherein x and y are two variables; x is the number ofiIs the ith data in the variable x,
is the average of the variable x;
2) calculating and measuring multiple collinearity severity of independent variable in the model by using the coefficient of variance expansion, and screening out the independent variable with the coefficient of variance expansion smaller than 5Independent variable；
In the formula, RiIs an independent variable xiThe negative correlation coefficient of the regression analysis was performed on the remaining independent variables.
5. The method according to claim 3, wherein the Logit model in step 23) has a linear relationship between the logarithmic probability Logit (Y) of the dependent variable Y and the independent variable X:
wherein p isjRepresenting the probability that the vehicle is at a level of risk of j; a value of j equal to 0 indicates safety; a value of j equal to 1 indicates a hazard; x is the number ofnRepresents the nth argument; beta is anDenotes xnThe coefficient of (a); alpha is alphajAnd representing the corresponding constant terms when j takes different values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111411639.5A CN114155742B (en) | 2021-11-23 | 2021-11-23 | Method for evaluating and early warning longitudinal driving risk of internet vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111411639.5A CN114155742B (en) | 2021-11-23 | 2021-11-23 | Method for evaluating and early warning longitudinal driving risk of internet vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114155742A true CN114155742A (en) | 2022-03-08 |
| CN114155742B CN114155742B (en) | 2023-03-17 |
Family
ID=80457453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111411639.5A Active CN114155742B (en) | 2021-11-23 | 2021-11-23 | Method for evaluating and early warning longitudinal driving risk of internet vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114155742B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116776204A (en) * | 2023-06-26 | 2023-09-19 | 清华大学 | Driver risk sensitivity differentiation characterization method, device, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102017011696A1 (en) * | 2017-12-18 | 2018-07-05 | Daimler Ag | Method and device for longitudinal movement control of a vehicle |
| CN110782125A (en) * | 2019-09-23 | 2020-02-11 | 同济大学 | Road safety risk degree evaluation method for automatically driving automobile |
| CN112711585A (en) * | 2021-01-12 | 2021-04-27 | 西安石油大学 | Expressway green traffic credit management system based on big data technology |
| CN113111502A (en) * | 2021-04-01 | 2021-07-13 | 同济大学 | Driver perception distance modeling method based on following model and driver characteristics |
-
2021
- 2021-11-23 CN CN202111411639.5A patent/CN114155742B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102017011696A1 (en) * | 2017-12-18 | 2018-07-05 | Daimler Ag | Method and device for longitudinal movement control of a vehicle |
| CN110782125A (en) * | 2019-09-23 | 2020-02-11 | 同济大学 | Road safety risk degree evaluation method for automatically driving automobile |
| CN112711585A (en) * | 2021-01-12 | 2021-04-27 | 西安石油大学 | Expressway green traffic credit management system based on big data technology |
| CN113111502A (en) * | 2021-04-01 | 2021-07-13 | 同济大学 | Driver perception distance modeling method based on following model and driver characteristics |
Non-Patent Citations (1)
| Title |
|---|
| 郭景华等: ""基于深度强化学习的驾驶员跟车模型研究"", 《汽车工程》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116776204A (en) * | 2023-06-26 | 2023-09-19 | 清华大学 | Driver risk sensitivity differentiation characterization method, device, equipment and medium |
| CN116776204B (en) * | 2023-06-26 | 2024-02-23 | 清华大学 | Driver risk sensitivity differentiation characterization method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114155742B (en) | 2023-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Feng et al. | Can vehicle longitudinal jerk be used to identify aggressive drivers? An examination using naturalistic driving data | |
| EP3960576A1 (en) | Method and system for analysing the control of a vehicle | |
| Chen et al. | A graphical modeling method for individual driving behavior and its application in driving safety analysis using GPS data | |
| CN111785023A (en) | Vehicle collision risk early warning method and system | |
| Kovaceva et al. | Identification of aggressive driving from naturalistic data in car-following situations | |
| CN110660270B (en) | Method for establishing vehicle collision risk evaluation model and collision risk evaluation method | |
| Mortazavi et al. | Effect of drowsiness on driving performance variables of commercial vehicle drivers | |
| CN113753059B (en) | Method for predicting takeover capacity of driver under automatic driving system | |
| Lv et al. | The influence of different factors on right-turn distracted driving behavior at intersections using naturalistic driving study data | |
| CN111401414A (en) | Natural driving data-based dangerous scene extraction and classification method | |
| Papazikou et al. | Detecting deviation from normal driving using SHRP2 NDS data | |
| Yu et al. | Effects of an integrated collision warning system on risk compensation behavior: An examination under naturalistic driving conditions | |
| Varotto et al. | Driver speed compliance following automatic incident detection: Insights from a naturalistic driving study | |
| CN114155742B (en) | Method for evaluating and early warning longitudinal driving risk of internet vehicle | |
| EP4126620B1 (en) | Coachable driver risk groups | |
| Stephens et al. | Do emotional appraisals of traffic situations influence driver behaviour? | |
| CN116001800B (en) | Vehicle driving risk information acquisition method and device, electronic equipment and medium | |
| Yang et al. | Individual differences in glance patterns under distraction in level 2 automated driving | |
| Papazikou et al. | Developing personalised braking and steering thresholds for driver support systems from SHRP2 NDS data | |
| Charly et al. | Identifying risky driving behavior: a field study using instrumented vehicles | |
| CN111775948B (en) | Driving behavior analysis method and device | |
| CN111341106B (en) | Traffic early warning method, device and equipment | |
| Lakatos et al. | An in-depth analysis of cycling and pedestrian accidents in Hungary | |
| Shichrur et al. | Convergent validity of vision based technology (VBT) among professional bus drivers | |
| Szumska et al. | Preliminary driving style classification of the professional drivers |
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 |