LU102622B1 - A Rear-end Collision Early Warning Method Based on Stratified COX Model - Google Patents
A Rear-end Collision Early Warning Method Based on Stratified COX Model Download PDFInfo
- Publication number
- LU102622B1 LU102622B1 LU102622A LU102622A LU102622B1 LU 102622 B1 LU102622 B1 LU 102622B1 LU 102622 A LU102622 A LU 102622A LU 102622 A LU102622 A LU 102622A LU 102622 B1 LU102622 B1 LU 102622B1
- Authority
- LU
- Luxembourg
- Prior art keywords
- delay time
- vehicle
- acceleration
- response delay
- following
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000004044 response Effects 0.000 claims abstract description 38
- 230000008569 process Effects 0.000 claims abstract description 5
- 230000001133 acceleration Effects 0.000 claims description 35
- 230000008859 change Effects 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000013517 stratification Methods 0.000 claims description 3
- 230000006461 physiological response Effects 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 235000019553 satiation Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/161—Decentralised systems, e.g. inter-vehicle communication
- G08G1/163—Decentralised systems, e.g. inter-vehicle communication involving continuous checking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/143—Alarm means
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
A rear-end collision early warning method based on stratified COX model. Firstly, acquiring vehicle state information and road environment information based on natural driving experimental data and determining driver response delay time. Then judging whether the data meet the PH hypothesis and the model coefficient is estimated. Based on the Internet of Vehicles, the vehicle state and road environment data in the actual driving process are obtained, and then these data are substituted into the calibrated COX or stratified COX model to get the probability distribution of driver response delay time. Then calculating the time-to-collision (TTC) and judging the size relationship between TTC and driver response delay time. Finally, based on the estimation result of the probability distribution, the probability that the driver response delay time is greater than the TTC in the current state is obtained, and an early warning is given.
Description
Description A Rear-end Collision Early Warning Method Based on Stratified COX Model
TECHNICAL FIELD The invention belongs to a method for judging driver response delay time in the process of car-following driving and a vehicle rear-end collision warning method based on TTC, it particularly relates to COX model and TTC calculation.
BACKGROUND With the continuous improvement of traffic demand, vehicle population and road environment complexity, the number of traffic accidents has also increased, resulting in a large number of casualties and economic losses. Rear-end collision is a major type of traffic accident, and there will be serious consequences when the following driver fails to respond in time after the emergency braking of the leading vehicle. The risk of rear-end collision can be evaluated by the vehicle collision time, which refers to the time required for the following vehicle to collide with the leading vehicle when the leading vehicle suddenly decelerates, and the following vehicle still drives at the current speed. When judging the risk by TTC, the physiological response time of driver is usually compared with TTC. When the TTC is less than the physiological response time, it is considered that the driver cannot make a rapid response to the upcoming collision event, which may lead to rear-end collision. However, in the complex driving environment, the process of the driver responding to the movement state change of the leading vehicle is not only affected by his own physiological response time, but also affected by such objective factors as the speed and acceleration of the leading and following vehicles and the relative distance between the two vehicles. BASAK K thinks that the variability of delay time should be considered when studying car-following problem, which will make the analysis results closer to the actual situation. PEI X considers that the driver response delay time follows the GAMMA distribution rather than a fixed value. By analysing the natural driving data, ARBABZADEH N found that the response delay time of drivers ranged from
0.58s to 8.0s and considered that there was a significant relationship between the response delay time and drivers’ own factors. Previous research results have pointed out the relationship between driver response delay time and external factors such as driving environment and vehicle state.
With the development of 5G technology, the Internet of Vehicles has become the future development direction. In terms of the Internet of Vehicles, it becomes easy to collect and communicate the data of vehicle motion state and road condition, and it also makes it easier to estimate the driver response delay time. In the past, TTC-based rear-end collision risk judgment was mostly based on a fixed driver physiological response time, without considering the influence of objective factors such as driving environment on the driver response delay time. Although rear-end collision early warning can be carried out, it does not consider the differences between different driving scenarios. In the invention, the COX proportional hazards model 1s adopted to estimate the probability distribution of the driver response delay time, and the influence of factors such as vehicle state and road environment on the driver response delay time is also considered in the model. Therefore, the probability that the driver respond delay time is greater than TTC will increase, which makes the rear- end collision early warning closer to the actual situation and improves the warning accuracy.
SUMMARY The purpose of the invention is to provide a stratified COX-based vehicle rear-end warning method which can improve the rear-end warning accuracy and calculate the probability of rear-end accidents.
Technical scheme A rear-end collision early warning method based on stratified COX model is composed of the following steps.
Step 1. In view of the target driver groups and common driving environment, the driver response delay time is calibrated based on COX proportional hazards model.
Step 2. Obtaining the position, speed, acceleration information and road environment information of the own vehicle and the leading vehicle through the Internet of Vehicles. Step 3. Calculating the safe car-following distance according to the climatic conditions of the road section and the speeds of the leading and following vehicles. And then comparing the calculation result of the relative position of the leading vehicle and the following vehicle with the predicted result of that to determine whether a rear-end collision occurs. Specifically, in Step 1 the driver response delay time 1s calibrated, and the specific model calibration includes following steps.
1) Carrying out a real vehicle experiment, measuring the vehicle state and road environment information, and identifying the driver response delay time. Further, the driver response delay time is determined by the acceleration and deceleration characteristic points of the leading and following vehicles. Wherein, the acceleration and deceleration change point of the leading vehicle is the starting point of the delay time, the acceleration and deceleration change point of the following vehicle is the termination point, and the change threshold of acceleration and deceleration is +0.15m / s° Recognition of deceleration starting point: filieP} da <0na, ok (a ,—a,>1na_ <O® ’ Recognition of deceleration termination point: fiJieP} Ha <0na, > pi (a, —a <-1na <0.15) Wherein, Fis the set of deceleration starting points; Lis the set of deceleration termination points; “ is the vehicle acceleration of section 7, m/s; “1 is the vehicle acceleration of the previous section of section ’, m/s. 2) Building COX proportional hazards model and estimating coefficient. (a) Determining whether the data conform to the PH hypothesis. If do, the hazard proportional coefficient does not change with time. (b) If the PH hypothesis is met, the COX proportional hazards model is constructed, and the coefficient is estimated.
N h(,X) =hOeplLAX . If the PH hypothesis is not met, the PH testing 1s carried out at first, and then a stratified COX proportional hazards model is constructed:
=p h, =, (©) exp}, BX, ;). In the formula, X is the independent variable vector of delay time influencing factors, A is the regression coefficient, and 40) is the benchmark hazard function of delay time.
Hypothesis testing shows that the regression coefficient does not belong to the constant independent variables, and p independent variables which do not satisfy the PH hypothesis are set as stratification variables Z with k classifications.
For different values of Z , there are different benchmark hazard functions AO , 87 12k In Step 2, the acquisition of the position, speed, acceleration information and road environment information of the following vehicle and the leading vehicle specifically includes the following steps. 1) Obtaining the position *, speed "| and acceleration % of the following vehicle as well as the position *o, speed % and acceleration “ of the leading vehicle by using on-board sensors such as millimetre-wave radar and GPS. 2) Getting environmental data such as weather information of the current road section through Internet of Vehicles.
In step 3, the process of judging whether a rear-end collision will occurred includes the following steps. 1) Inputting data to obtain the probability distribution of driver response delay time. 2) Calculate TTC,
TTC, = Xo, =X, —L
Vie 7 Vos
3) Based on the probability distribution of driver response delay time estimated by COX proportional hazards model, judging the probability that driver response delay time 1s greater than TTC.
Beneficial effect Compared with the prior art, the invention adopts the probability distribution estimation method of driver response delay time based on COX model and further proposes the rear- end collision warning method combined with TTC.
By considering the objective factors such as vehicle motion state and road environment, the probability distribution of driver reaction delay time in different driving scenes 1s estimated, and the invention can improve the TTC-based rear-end collision warning accuracy.
BRIEF DESCRIPTION OF THE FIGURES Figure 1 is a flow chart of rear-end collision early warning according to the present invention. Figure 2 is a schematic diagram for determining response delay time. Figure 3 shows the estimated results of the stratified COX proportional hazards model.
DESCRIPTION OF THE INVENTION The invention will be further elucidated with reference to the figures and specific embodiments. As for the rear-end collision early warning method based on stratified COX model, the driver response delay time is calibrated firstly according to the target driver groups and common driving environment, based on COX proportional hazards model, specifically comprising the following steps. (1.1) Carrying out a real vehicle experiment, measuring the vehicle state and road environment information, and identifying the driver response delay time. Further, the driver response delay time is determined by the acceleration and deceleration characteristic points of the leading and following vehicles. Wherein, the acceleration and deceleration change point of the leading vehicle is the starting point of the delay time, the acceleration and deceleration change point of the following vehicle is the termination point, and the change threshold of acceleration and deceleration is +0.15m/s" | The identification diagram is shown in Figure 2. Recognition of deceleration starting point: frreny= fo <0na, DR (a, ,-a >1na,, <0 Recognition of deceleration termination point: fireny={ <0na, “owt (a, —a <-1na <0.15)
Wherein, Pis the set of deceleration starting points; Lis the set of deceleration termination points; “ is the vehicle acceleration of section 7, m/s; “1 is the vehicle acceleration of the previous section of section ’, m/s. 2) Building COX proportional hazards model and estimating coefficient. (a) Determining whether the data conform to the PH hypothesis. If do, the hazard proportional coefficient does not change with time. (b) If the PH hypothesis is met, the COX proportional hazards model is constructed, and the coefficient is estimated.
N h(t, X) = hy()exp[Y_ BX]. i=l If the PH hypothesis is not met, the PH testing 1s carried out at first, and then a stratified COX proportional hazards model is constructed: 5-p h, (Oh, exp X AX).
In the formula, X is the independent variable vector of delay time influencing factors, A is the regression coefficient, and fm) is the benchmark hazard function of delay time. Hypothesis testing shows that the regression coefficient does not belong to the constant independent variables, and p independent variables which do not satisfy the PH hypothesis are set as stratification variables Z with k classifications. For different values of Z , there are different benchmark hazard functions AO , 87 12k The independent variable vector definition of influencing factors and pH test results are shown in Table 1 and Table 2. Table 1 Independent Variable Vector Definition of Influencing Factors Variable name Variable type Value Dichotomous Daytime- X, =0 Light conditions X, variable Evening- X, =1 v,<75m/s-X,=1 Categorical Leading vehicle speed X, Vv, <125m/s-X,=2 variable v,<175m/s-X,=3
Acceleration of leading Dichotomous @ <O0m/s*-X,=0 vehicle X, variable a,>0m/s*-X, =1 ‘Relative distance between leading and following Continuous X,=p,-p, M vehicles X, variable Acceleration change state of Dichotomous Constant speed - Variable speed - X; =0 leading vehicle X, variable Variable speed - Constant speed - X; =1 Table 2 pH Test Results Variable name ~~ Chi-square Pvalue measure “Light conditions X 00109 ____o9170 Leading vehicle speed X, 0.4352 0.5090 Acceleration of leading vehicle X, 18.9456 0.000 0 (non-satiation) Relative distance between leading and 2.2202 0.1360 following vehicles X, Acceleration change state of leading 5.5035 0.0190 vehicle X, The leading vehicle does not meet the PH hypothesis, so a stratified COX model is constructed.
The driver response delay time estimated by the model is shown in Figure 3, and the parameter estimation results are shown in Table 3. Table 3 Parameter Estimation Results of the Stratified COX Model “Independent variable Regression Proportional Standard error of P coefficient hazards regression coefficient value ‘Light conditions X, 0.0941 10987 01603 056
Leading vehicle speed X, 0.0330 1.033 5 0.097 6 0.74 Relative distance between -0.006 2 0.993 8 0.002 8 0.03 leading and following vehicles X, Acceleration change state -0.4368 0.646 1 0.138 1 0.00 of leading vehicle X, (2) Obtaining the position, speed, acceleration information and road environment | information of the own vehicle and the leading vehicle through the Internet of Vehicles. (2.1) Obtaining the position “, speed " and acceleration % of the following vehicle as well as the position * speed "° and acceleration “ of the leading vehicle by using on- board sensors such as millimetre-wave radar and GPS.
(2.2) Getting environmental data such as weather information of the current road section through Internet of Vehicles. 3) Calculating the safe car-following distance according to the climatic conditions of the road section and the speeds of the leading and following vehicles. And then comparing the calculation result of the relative position of the leading vehicle and the following vehicle with the predicted result of that to determine whether a rear-end collision occurs. (3.1) Inputting data to obtain the probability distribution of driver response delay time. (3.2) Calculate TTC, pre, + Ses Au Vi = Vo, (3.3) Based on the probability distribution of driver response delay time estimated by COX proportional hazards model, judging the probability that driver response delay time is greater than TTC. Example : Vehicle status and weather conditions are obtained through the Internet of Vehicles. The probability distribution of driver response delay time estimated under known conditions is shown in Figure 3. When TTC is 2.5 seconds and the car in front is in deceleration stage,
the probability of driver reaction delay time is less than TTC and the risk of rear-end collision is about 45%.
As mentioned above, the embodiments only describe the preferred embodiments of the present invention, and do not limit the scope of the present invention. That is to say, all the embodiments not described above, and the equivalent changes and modifications made according to the patent application scope of the invention shall belong to the technical scope of the invention.
Claims (4)
1. À rear-end collision early warning method based on stratified COX model, characterized by following steps; step 1, in view of the target driver groups and common driving environment, the driver response delay time 1s calibrated based on COX proportional hazards model; step 2, obtaining the position, speed, acceleration information and road environment information of the own vehicle and the leading vehicle through the Internet of Vehicles; step 3, calculating the safe car-following distance according to the climatic conditions of the road section and the speeds of the leading and following vehicles; and then comparing the calculation result of the relative position of the leading vehicle and the following vehicle with the predicted result of that to determine whether a rear-end collision occurs;
2. The rear-end collision early warning method based on stratified COX model as stated in Claim 1, characterized in that the driver response delay time is calibrated in Step 1, and the specific model calibration includes following steps; 1) carrying out a real vehicle experiment, measuring the vehicle state and road environment information, and identifying the driver response delay time; further, the driver response delay time is determined by the acceleration and deceleration characteristic points of the leading and following vehicles; wherein, the acceleration and deceleration change point of the leading vehicle is the starting point of the delay time, the acceleration and deceleration change point of the following vehicle is the termination point, and the change threshold of acceleration and deceleration is +0.15m / s° ; Recognition of deceleration starting point: filieP} À |Ca, Da, <Ona, ok (a, —a,>1na <O ? Recognition of deceleration termination point: plreny= (LE <0na, grad (a, ,—a <-1na <0.15 wherein, Lis the set of deceleration starting points: Ë is the set of deceleration termination points; % is the vehicle acceleration of section !, m/s; “1 is the vehicle acceleration of the previous section of section ‘, m/s; 2) Building COX proportional hazards model and estimating coefficient; (a) determining whether the data conform to the PH hypothesis; if do, the hazard proportional coefficient does not change with time; (b) if the PH hypothesis is met, the COX proportional hazards model is constructed, and the coefficient is estimated;
N h(t, X) =h, (0 exp), AX 1; i=1 If the PH hypothesis is not met, the PH testing is carried out at first, and then a stratified COX proportional hazards model is constructed: 5-p h, (Oh, exp AX.) ; In the formula, X is the independent variable vector of delay time influencing factors, A is the regression coefficient, and MC is the benchmark hazard function of delay time; hypothesis testing shows that the regression coefficient does not belong to the constant independent variables, and p independent variables which do not satisfy the PH hypothesis are set as stratification variables Z with k classifications; for different values of Z , there . . h(t = ve are different benchmark hazard functions be (1) , 87 12, k
3. The rear-end collision early warning method based on stratified COX model as stated in Claim 1, characterized in that in Step 2, the acquisition of the position, speed, acceleration information and road environment information of the following vehicle and the leading vehicle specifically includes the following steps; 1) obtaining the position “, speed " and acceleration % of the following vehicle as well as the position *, speed " and acceleration “ of the leading vehicle by using on-board sensors such as millimetre-wave radar and GPS; 2) getting environmental data such as weather information of the current road section through Internet of Vehicles.
4. The rear-end collision early warning method based on stratified COX model as stated in Claim 1, characterized in that in step 3, the process of judging whether a rear-end collision will occurred includes the following steps; 1) inputting data to obtain the probability distribution of driver response delay time; 2) calculate TTC, TTC, _ Xo, 7 Ar -L .
Vie Vou ’ 3) based on the probability distribution of driver response delay time estimated by COX proportional hazards model, judging the probability that driver response delay time is greater than TTC.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| LU102622A LU102622B1 (en) | 2021-03-05 | 2021-03-05 | A Rear-end Collision Early Warning Method Based on Stratified COX Model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| LU102622A LU102622B1 (en) | 2021-03-05 | 2021-03-05 | A Rear-end Collision Early Warning Method Based on Stratified COX Model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| LU102622B1 true LU102622B1 (en) | 2021-09-06 |
Family
ID=77614911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| LU102622A LU102622B1 (en) | 2021-03-05 | 2021-03-05 | A Rear-end Collision Early Warning Method Based on Stratified COX Model |
Country Status (1)
| Country | Link |
|---|---|
| LU (1) | LU102622B1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116142154A (en) * | 2023-04-21 | 2023-05-23 | 南京飞恩微电子有限公司 | Hybrid brake-by-wire system |
-
2021
- 2021-03-05 LU LU102622A patent/LU102622B1/en active IP Right Grant
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116142154A (en) * | 2023-04-21 | 2023-05-23 | 南京飞恩微电子有限公司 | Hybrid brake-by-wire system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Moujahid et al. | Machine learning techniques in ADAS: A review | |
| Katare et al. | Embedded system enabled vehicle collision detection: an ANN classifier | |
| CN113635897B (en) | Safe driving early warning method based on risk field | |
| CN103531042A (en) | Rear-end collision pre-warning method based on driver types | |
| CN111398989A (en) | Performance analysis method and test equipment of driving assistance system | |
| DE102013222634A1 (en) | A method of predicting a road friction coefficient and method of operating a motor vehicle | |
| JP2022532941A (en) | Devices and methods for processing vehicle signals to calculate behavioral risk measures | |
| LU102622B1 (en) | A Rear-end Collision Early Warning Method Based on Stratified COX Model | |
| CN113962011A (en) | Electric automobile braking system model and establishing method thereof | |
| Zhang et al. | A scene comprehensive safety evaluation method based on binocular camera | |
| CN113763702A (en) | V2V-based humanization-friendly front collision early warning system and early warning method | |
| CN114255614A (en) | Intelligent expressway vehicle deceleration early warning method and system based on vehicle-mounted smart phone and automobile data recorder | |
| CN110033617A (en) | A kind of train tracing model assessment system and method towards natural driving data | |
| CN114354216A (en) | V2X collision early warning real vehicle test system and method based on high-precision positioning | |
| CN117864121B (en) | Distance dynamic monitoring method, system, equipment and storage medium | |
| CN110588605B (en) | Active braking control system and control method for preventing accelerator pedal from being stepped by mistake | |
| CN114064656B (en) | Automatic driving scene recognition and conversion method based on road end perception system | |
| Zardosht et al. | Identifying Driver Behavior in Preturning Maneuvers Using In‐Vehicle CANbus Signals | |
| CN114734966A (en) | Automatic emergency braking system and method based on camera and cloud real-time map | |
| CN112596388B (en) | LSTM neural network AEB system control method based on driver data | |
| Feng et al. | Modelling and simulation for safe following distance based on vehicle braking process | |
| CN115979679A (en) | Method, apparatus and storage medium for testing actual road of automatic driving system | |
| CN111348038A (en) | Rear-end collision early warning method based on VARMA model short-time prediction | |
| CN114056332B (en) | Intelligent automobile following decision and control method based on cognitive risk balance | |
| CN111369829A (en) | Vehicle rear-end collision early warning method based on layered COX |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FG | Patent granted |
Effective date: 20210906 |