CN114148321B - Automatic emergency braking and safety evaluation method considering collision risk - Google Patents
Automatic emergency braking and safety evaluation method considering collision risk Download PDFInfo
- Publication number
- CN114148321B CN114148321B CN202111387055.9A CN202111387055A CN114148321B CN 114148321 B CN114148321 B CN 114148321B CN 202111387055 A CN202111387055 A CN 202111387055A CN 114148321 B CN114148321 B CN 114148321B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- early warning
- braking
- decision
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title abstract description 12
- 230000035484 reaction time Effects 0.000 claims abstract description 11
- 238000013058 risk prediction model Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 14
- 230000001133 acceleration Effects 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 101150092874 DBR1 gene Proteins 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 3
- 238000011835 investigation Methods 0.000 claims description 3
- 238000007477 logistic regression Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 3
- 238000012549 training Methods 0.000 abstract description 2
- 230000001960 triggered effect Effects 0.000 description 19
- 238000009826 distribution Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 6
- 230000004044 response Effects 0.000 description 6
- 238000013500 data storage Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012502 risk assessment Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Images
Classifications
-
- 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
- B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
- B60Q9/008—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling for anti-collision purposes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60T—VEHICLE BRAKE CONTROL SYSTEMS OR PARTS THEREOF; BRAKE CONTROL SYSTEMS OR PARTS THEREOF, IN GENERAL; ARRANGEMENT OF BRAKING ELEMENTS ON VEHICLES IN GENERAL; PORTABLE DEVICES FOR PREVENTING UNWANTED MOVEMENT OF VEHICLES; VEHICLE MODIFICATIONS TO FACILITATE COOLING OF BRAKES
- B60T7/00—Brake-action initiating means
- B60T7/12—Brake-action initiating means for automatic initiation; for initiation not subject to will of driver or passenger
- B60T7/22—Brake-action initiating means for automatic initiation; for initiation not subject to will of driver or passenger initiated by contact of vehicle, e.g. bumper, with an external object, e.g. another vehicle, or by means of contactless obstacle detectors mounted on the vehicle
-
- 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
-
- 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)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of road traffic safety, in particular to an automatic emergency braking and safety evaluation method considering collision risk. According to the automatic emergency braking and safety evaluation method considering the collision risk, provided by the invention, on the premise of considering the personalized reaction time of a driver, the collision risk, the relative distance of the vehicle and the collision time are comprehensively considered, the risk driving behavior of the driver is early warned in time, the driver is reminded to take the risk avoidance measures as soon as possible, the forced braking is carried out at the critical moment, and the personal safety of the driver is protected. Meanwhile, the influence of the road adhesion coefficient and the road gradient on the maximum braking deceleration of the vehicle is considered, so that the vehicle can be well adapted to the change of different road conditions, the early warning and autonomous braking time is more accurate, and the reliability of the system is improved. On the other hand, the risk driving behavior and the risk avoiding capability of the driver can be evaluated, so that the driver can know the emergency risk avoiding capability of the driver, and the targeted training can be carried out.
Description
Technical Field
The invention relates to the technical field of road traffic safety, in particular to an automatic emergency braking and safety evaluation method considering collision risk.
Background
With the gradual increase of the quantity of the automobile, driving travel becomes a travel mode which is generally selected, and in a complex road traffic system, the risk driving behavior of a driver has a great influence on traffic safety. Rear-end collision is a common accident situation, threatens the personal safety of a vehicle driver, and an automatic emergency braking system (AEB) is used as an active safety technology, and is a system capable of monitoring the running environment in front of a vehicle in real time and automatically starting the vehicle braking system to slow down the vehicle when a collision danger possibly occurs so as to avoid collision or reduce collision. However, most of the existing automatic emergency braking systems are built based on safe distance or time parameter algorithm, and the two modes are combined and applied in a small amount, and the braking deceleration is calculated by adopting a preset fixed value in many cases, so that the influence of road adhesion coefficient and road gradient on the braking efficiency of the vehicle is less considered. The method can not be well adapted to the change of road conditions, and early warning phenomenon of early warning or late warning can occur at the early warning moment based on system parameter calculation, so that the reliability of the system is affected.
Disclosure of Invention
In view of the above-mentioned shortcomings of the background art, an object of the present invention is to provide an automatic emergency braking and safety evaluation method considering collision risk.
The aim of the invention can be achieved by the following technical scheme:
an automatic emergency braking and safety evaluation method considering collision risk specifically comprises the following steps: the system comprises a vehicle running state acquisition device, a road environment state acquisition device, a control decision device, an information storage device, an early warning device and a brake control device. The vehicle running state acquisition device is mainly used for acquiring current speed, vehicle deceleration, vehicle distance between the vehicle and a front workshop and relative speed data of the vehicle and the front vehicle. The road environment state acquisition device is mainly used for acquiring road surface adhesion coefficients and road gradients. The control decision device is mainly used for receiving the vehicle state and road state data transmitted by the vehicle running state acquisition device and the road environment state acquisition device, extracting data information in the information storage device, making decisions based on an automatic emergency braking algorithm and a vehicle collision risk prediction model, and transmitting decision information to the early warning device, the information storage device and the braking control device of the vehicle. The information storage device is mainly used for storing data information of triggering system events so as to be extracted and used by a control decision device or a technician. The early warning device is mainly used for receiving the decision information of the control decision device and adopting a corresponding early warning reminding mode to remind a driver to pay attention to the speed control or timely avoid danger. The braking control device is connected with the vehicle braking control system and is used for receiving the decision information of the control decision device and deciding whether to take active forced braking measure or not.
Further, the road environment state acquisition device transmits the acquired road surface adhesion coefficient and road gradient data to the control decision device, and the control decision device calculates the maximum braking deceleration which can be adopted on the current running road of the vehicle according to the road surface adhesion coefficient and the road gradient data by the following formula:
a max ＝g(sinθ+μcosθ)
wherein a is max The maximum braking deceleration of the vehicle is g, g is gravitational acceleration, θ is road gradient, and μ is road surface adhesion coefficient.
The vehicle running state acquisition device acquires the current speed, deceleration, vehicle distance between the vehicle and a front workshop and vehicle speed data relative to the front vehicle, and transmits the data to the control decision device, the control decision device receives the data transmitted by the road environment state acquisition device and the vehicle running state acquisition device, and the moment of starting early warning and starting forced braking intervention risk avoidance of the vehicle is calculated by the following method:
the control decision device obtains the maximum braking deceleration which can be adopted by the current vehicle running road based on the road environment state parameters, meanwhile, the control decision device receives vehicle running parameter data, calculates and obtains an early warning critical distance threshold between the front vehicle and the self vehicle based on the following formula, when the relative distance between the self vehicle and the front vehicle is smaller than or equal to the calculated early warning critical distance threshold, the control decision device makes an early warning decision and transmits the early warning decision to the early warning device, and the early warning device receives early warning decision information and makes corresponding early warning reminding for a vehicle driver. The front vehicle is a front vehicle which runs on the same lane as the own vehicle and has the shortest relative distance with the own vehicle. The early warning critical distance threshold value calculation formula is as follows:
wherein d is the pre-warning critical distance between the front vehicle and the own vehicle, v is the current speed of the own vehicle, and τ=t+t r ，t r Delay time for the brake; t is the reaction time of the driver, t=0.8+x, where x > 0 is the reaction time adjustment parameter for adjusting the reaction time of the driver in seconds. v rel The relative speed between the own vehicle and the front vehicle; d, d 0 Is the minimum safe distance between two vehicles after the vehicles stop. According to the relative distance between the own vehicle and the front vehicle and the relative vehicle speed, when the own vehicle speed is greater than the front vehicle speed, the control decision device calculates a TTC value based on the vehicle running state parameter, and when the TTC value is not greater than a certain threshold value, the control decision device also makes an early warning decision and transmits the early warning decision to the early warning device, and the early warning device receives early warning decision information and makes corresponding early warning reminding for a vehicle driver. The TTC early warning critical value is calculated by the following steps:
wherein d rel Is the relative distance between the own vehicle and the front vehicle. And constructing a vehicle collision risk prediction model based on the vehicle speed, the relative distance between two vehicles and the braking deceleration of the driver by using a binary logistic regression method. Based on the vehicle collision risk prediction model and the vehicle relative distance, the vehicle speed of the collision accident of the vehicle is predicted, and compared with the current vehicle speed of the own vehicle. When the predicted speed is less than or equal to the current speed of the vehicle, the control decision device controls the early warning device to remind the driver to take deceleration measures in time.
Distance-based early warning critical distance threshold d and time-based early warning critical value T br And predicting the vehicle speed at the risk of vehicle collision. The output results of the three early warning calculation modes are respectively two classification variables, and m represents the accumulated sum of the decision results of the three early warning modes. The final output result of the control decision device is a multi-element classification result, the respective discrimination results are coupled and applied to the early warning decision of the early warning system based on three early warning discrimination modes, and the early warning is carried outAnd transmitting the decision result to an early warning device, and carrying out corresponding early warning operation by the early warning device based on the final early warning decision instruction. The final early warning decision embodiment is as follows:
when the own vehicle continues to approach the front vehicle, the control decision device calculates a system braking critical distance threshold value based on the following formula, and dbr1 and dbr2 are respectively calculated and compared with the current distance of the vehicle, and the braking critical distance d is calculated br The calculation method is as follows:
d br1 ＝v rel τ+0.5a max τ 2
d br2 ＝TTC*v rel +d 0
the calculated output result of the braking critical distance is a binary variable 0 or 1, and when the relative distance between the own vehicle and the front vehicle is smaller than or equal to the calculated braking critical distance, the output result is 1; when the relative distance between the own vehicle and the front vehicle is larger than the calculated braking critical distance, the output result is 0, the judging result is coupled and applied to the forced braking decision of the system based on two judging modes, and s represents the sum of the two judging output results. The final braking decision output signal is as follows:
in the initial stage of the system, an initial vehicle collision risk prediction model can be constructed based on rear-end collision accident cases in a deep accident investigation database. When the system triggering event occurs in the actual driving process of the vehicle, the control decision device stores the vehicle speed at the early warning moment, the relative distance between the vehicle and the front workshop and the maximum braking deceleration adopted by the driver before the forced intervention of the system, whether the system is braked forcedly or not and whether a collision result is used as event data in the data storage device. Whether the collision result can be judged according to the TTC value, when the TTC value is smaller than or equal to 1.5s, the collision accident happens to the vehicle, and in the actual running process of the vehicle, after a certain amount of new observation values are accumulated, the system automatically updates the collision risk prediction model.
The specific early warning and braking implementation modes of the system are as follows:
(1) When f (x) =0, the system does not make early warning and braking operations, and does not interfere with the driving behavior of the driver and the running state of the vehicle;
(2) When f (x) =1, the early warning device triggers and activates and reminds a driver to pay attention to control the vehicle speed, so that rear-end collision accidents are prevented;
(3) When f (x) =2, the early warning device triggers activation and reminds the driver of performing emergency deceleration operation.
(4) When g (x) =0, the system does not perform forced braking intervention, and when g (x) =1, the control decision device makes forced braking decision and transmits the braking decision to the braking control device, and the braking control device receives braking decision information and immediately performs forced braking on the own vehicle.
Further, the brake control device counts the system triggering frequency of the driver in the daily driving process, and if the driver triggers the early warning function, whether the forced intervention of the system to the vehicle is triggered or not follows Beta (a, b) distribution, wherein the parameter a represents the accumulated times of the early warning of the vehicle triggering system but the forced braking intervention is not triggered, and the parameter b represents the accumulated times of the forced braking intervention triggered by the vehicle. When a new system triggering event occurs, the prior information of whether to trigger the vehicle braking intervention measure after the system triggers the early warning function is updated by a new observed value after the system triggering event. The Beta distribution and the binomial distribution are conjugate prior distributions. Therefore, the posterior distribution is also a Beta (c, d) distribution, wherein c=a+z, d=b+1-z, z is an observed value of whether the system adopts braking intervention when the system is triggered, if the braking intervention of the system is triggered, the value of z is 0, and if the forced intervention is not triggered, the value of z is 1, so that the early warning response probability of a driver to the system can be estimated according to the observed value.
Furthermore, the control decision device can combine event data record and driver collision risk prediction model in the data storage device, can carry out statistical analysis on the vehicle speed, the relative distance between two vehicles and the maximum braking deceleration data of the driver when the system is triggered and the early warning response probability of the driver, and output a driving risk analysis report, carries out parameterization on the habit of the driver in following the vehicle for avoiding danger and the driving risk, and is helpful for comprehensively knowing the risk avoidance behavior of the driver when the system is triggered. Alternatively, analysis of various data acquired during system triggering can be achieved by the control decision device based on a statistical manner, by connecting the output end of the control decision device with the vehicle-mounted display. And constructing a visual driving risk assessment result display platform. And when the system is triggered, the system emergency response probability and the historical driving behavior parameters of the driver are statistically and visually displayed, so that comprehensive evaluation of the risk avoiding driving capability of the driver is facilitated.
Compared with the prior art, the invention has the beneficial effects that:
according to the automatic emergency braking and safety evaluation method considering the collision risk, provided by the invention, on the premise of considering the personalized reaction time of a driver, the collision risk, the relative distance of the vehicle and the collision time are comprehensively considered, the risk driving behavior of the driver is early warned in time, the driver is reminded to take the risk avoidance measures as soon as possible, the forced braking is carried out at the critical moment, and the personal safety of the driver is protected. Meanwhile, the influence of the road adhesion coefficient and the road gradient on the maximum braking deceleration of the vehicle is considered, so that the vehicle can be well adapted to the change of different road conditions, the early warning and autonomous braking time is more accurate, and the reliability of the system is improved. On the other hand, based on Bayesian distribution and in combination with the risk running state of the vehicle when the system is triggered, the risk driving behavior and the risk avoiding capability of the driver are evaluated, so that the driver's emergency risk avoiding capability is known, and targeted training is carried out.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to those skilled in the art that other drawings can be obtained according to these drawings without inventive effort;
FIG. 1 is a schematic flow diagram of an automatic emergency braking system of the present invention;
FIG. 2 is a flow chart of the security evaluation method of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides an automatic emergency braking and safety evaluation method considering collision risk, which specifically comprises the following steps: the system comprises a vehicle running state acquisition device, a road environment state acquisition device, a control decision device, an information storage device, an early warning device and a brake control device. The vehicle running state acquisition device and the road environment state acquisition device transmit detected data information to the control decision device, the control decision device receives the vehicle running state and road environment state data, and makes a control decision based on the automatic emergency braking system considering collision risk, and transmits the decision information to the information storage device, the early warning device and the braking control device, the information storage device receives the decision information of the control decision device to write or read corresponding data, the early warning device receives the decision information of the control decision device to correspondingly warn a driver, and the braking control device is connected with the vehicle braking control system and is used for receiving the decision information of the control decision device to forcedly brake a vehicle.
Specifically, the vehicle running state acquisition device is mainly used for acquiring current speed, deceleration, vehicle distance between the vehicle and a front workshop and relative speed data of the vehicle and the front vehicle.
The vehicle running state acquisition device can select a speed measuring sensor, an acceleration sensor, a distance measuring sensor and the like.
The road environment state acquisition device is mainly used for acquiring road surface adhesion coefficients and road gradients.
Road surface adhesion coefficient the road surface adhesion coefficient can be estimated using a tire road surface adhesion coefficient estimation model or Effect-based estimation algorithm proposed by korea university Kyongsu et al. The road grade θ may be measured using a VN-100 attitude sensor.
The control decision device is mainly used for receiving the data transmitted by the vehicle running state acquisition device and the road environment state acquisition device, extracting data information in the information storage device, making corresponding decisions based on an automatic emergency braking algorithm and a vehicle collision risk prediction model calculation result, and transmitting decision information to the early warning device, the information storage device and the self-vehicle braking control device. The control decision device can select 8051 singlechip.
The information storage device is mainly used for storing data information of triggering system events so as to be extracted and used by a control decision device or a technician. The information storage device may be a disk or memory that controls the decision making device to read and write data.
The early warning device is mainly used for receiving the decision information of the control decision device and adopting a corresponding early warning reminding mode. The early warning device can be a loudspeaker.
The braking control device is connected with the vehicle braking control system and is used for receiving the decision information of the control decision device and deciding whether to take braking measures or not.
Further, the road environment state acquisition device transmits the acquired road surface adhesion coefficient and road gradient data to the control decision device, and the control decision device calculates the maximum braking deceleration which can be adopted on the current running road of the vehicle according to the road surface adhesion coefficient and the road gradient data by the following formula:
a max ＝g(sinθ+μcosθ)
wherein a is max The maximum braking deceleration of the vehicle is g, g is gravitational acceleration, θ is road gradient, and μ is road surface adhesion coefficient.
The vehicle running state acquisition device acquires the current speed, deceleration, vehicle distance between the vehicle and a front workshop and vehicle speed data relative to the front vehicle, and transmits the data to the control decision device, the control decision device receives the data transmitted by the road environment state acquisition device and the vehicle running state acquisition device, and the moment of starting early warning and starting forced braking intervention risk avoidance of the vehicle is calculated by the following method:
the control decision device obtains the maximum braking deceleration which can be adopted by the current vehicle running road based on the road environment state parameters, meanwhile, the control decision device receives vehicle running parameter data, calculates and obtains an early warning critical distance threshold between the front vehicle and the self vehicle based on the following formula, when the relative distance between the self vehicle and the front vehicle is smaller than or equal to the calculated early warning critical distance threshold, the control decision device makes an early warning decision and transmits the early warning decision to the early warning device, and the early warning device receives early warning decision information and makes corresponding early warning reminding for a vehicle driver. The front vehicle is a front vehicle which runs on the same lane as the own vehicle and has the shortest relative distance with the own vehicle. The early warning critical distance threshold value calculation formula is as follows:
wherein d is the pre-warning critical distance between the front vehicle and the own vehicle, v is the current speed of the own vehicle, and τ=t+t r ，t r Delay time for the brake; t is the reaction time of the driver in seconds. Specifically, the reaction time of the driver in the dangerous scene may be measured based on the simulated driving apparatus or the like before the driver performs the actual driving. So that the tset value is the measured driver reaction time. v rel The relative speed between the own vehicle and the front vehicle; d, d 0 The minimum safe distance between two vehicles after the vehicles stop can be 5m. According to the relative distance between the own vehicle and the front vehicle and the relative vehicle speed, when the own vehicle speed is larger than the front vehicle speed, the control decision device calculates a TTC value based on the vehicle running state parameter, and when the TTC value is larger than the early warning critical value T br When the decision device is controlled to output a 0 signal; when the TTC value is not greater than the early warning critical value T br And when the decision device is controlled to output a 1 signal. TTC and early warning critical value T br The calculation mode of (a) is as follows:
wherein d rel The relative distance between the vehicle and the front vehicle is u, and u is a correction coefficient.
Based on the rear-end accident data set and the running history data of the vehicle, a binary logistic regression method is used for constructing a vehicle collision risk prediction model based on the speed, the relative distance between two vehicles and the braking deceleration of the driver. Based on the vehicle collision risk prediction model and the vehicle relative distance, the vehicle speed of the collision accident of the vehicle is predicted, and compared with the current vehicle speed of the own vehicle. When the predicted vehicle speed is greater than the current vehicle speed of the own vehicle, the control decision device controls the output of a 0 signal; when the predicted speed is less than or equal to the current speed of the own vehicle, the control decision device controls the output 1 signal. In the initial stage of the system, a vehicle collision risk prediction model can be constructed based on rear-end collision accident cases in a deep accident investigation database, the model is input into a control decision device, and the vehicle speed of a collision accident of the vehicle is predicted based on the vehicle collision risk prediction model and the vehicle relative distance and the maximum deceleration of a driver.
Distance-based early warning critical distance threshold d and time-based early warning critical value T br And predicting the vehicle speed at the risk of vehicle collision. The output results of the three early warning calculation modes are respectively two classification variables, and m represents the accumulated sum of the decision results of the three early warning modes. The final output result of the control decision device is a multi-element classification result, the respective discrimination results are coupled and applied to the early warning decision of the early warning system based on three early warning discrimination modes, the early warning decision result is transmitted to the early warning device, and the early warning device carries out corresponding early warning operation based on the final early warning decision instruction. The final early warning decision embodiment is as follows:
the specific early warning implementation mode of the system is as follows:
(4) When f (x) =0, the system does not make early warning and braking operations, and does not interfere with the driving behavior of the driver and the running state of the vehicle.
(5) When f (x) =1, the early warning device triggers and activates and reminds a driver to pay attention to control the vehicle speed, and rear-end collision accidents are prevented.
(6) When f (x) =2, the early warning device triggers activation and reminds the driver of performing emergency deceleration operation.
When the own vehicle continues to approach the front vehicle, the control decision device calculates a system braking critical distance threshold value based on the following formula, and dbr1 and dbr2 are respectively calculated and compared with the current distance of the vehicle, and the braking critical distance d is calculated br The calculation method is as follows:
d br1 ＝v rel τ+0.5a max τ 2
d br2 ＝TTC*v rel +d 0
the calculated output result of the braking critical distance is a binary variable 0 or 1, and when the relative distance between the own vehicle and the front vehicle is smaller than or equal to the calculated braking critical distance, the output result is 1; when the relative distance between the own vehicle and the front vehicle is larger than the calculated braking critical distance, the output result is 0, the judging result is coupled and applied to the forced braking decision of the system based on two judging modes, and s represents the sum of the two judging output results. The final braking decision embodiment is as follows:
when g (x) =0, the system does not perform forced braking intervention, and when g (x) =1, the control decision device makes forced braking decision and transmits the braking decision to the braking control device, and the braking control device receives braking decision information and immediately performs forced braking on the own vehicle.
When the system triggering event occurs in the actual driving process of the vehicle, the control decision device stores the vehicle speed at the early warning moment, the relative distance between the vehicle and the front workshop, the relative vehicle speed and the maximum braking deceleration adopted by the driver before the forced intervention of the system, whether the system is braked forcedly or not and whether a collision result is used as event data in the data storage device. Whether the collision result can be judged according to the TTC value, when the TTC value is smaller than or equal to 1.5s, the collision accident happens to the vehicle, and in the actual running process of the vehicle, after a certain amount of new observation values are accumulated, the system automatically updates the collision risk prediction model.
Further, the brake control device counts the system triggering frequency of the driver in the daily driving process, and if the driver triggers the early warning function, whether the forced intervention of the system to the vehicle is triggered or not follows Beta (a, b) distribution, wherein the parameter a represents the accumulated times of the early warning of the vehicle triggering system but the forced braking intervention is not triggered, and the parameter b represents the accumulated times of the forced braking intervention triggered by the vehicle. When a new system triggering event occurs, the prior information of whether to trigger the vehicle braking intervention measure after the system triggers the early warning function is updated by a new observed value after the system triggering event. The Beta distribution and the binomial distribution are conjugate prior distributions. Therefore, the posterior distribution is also a Beta (c, d) distribution, wherein c=a+z, d=b+1-z, z is an observation value of whether the system adopts braking intervention when the system is triggered, if the braking intervention of the system is triggered, the value of z is 0, and if the forced intervention is not triggered, the value of z is 1, so that the probability distribution of the early warning response of the driver to the system can be estimated according to the probability distribution.
Furthermore, the control decision device can combine event data record and driver collision risk prediction model in the data storage device, can carry out statistical analysis on the vehicle speed, the relative distance between two vehicles and the maximum braking deceleration data of the driver when the system is triggered and the early warning response probability of the driver, and output a driving risk analysis report, and parameterize the following vehicle risk-avoidance driving behavior habit and the risk driving behavior of the driver, thereby being beneficial to comprehensively knowing the risk-avoidance behavior of the driver when the system is triggered. Alternatively, analysis of various data acquired during system triggering can be achieved by the control decision device based on a statistical manner, by connecting the output end of the control decision device with the vehicle-mounted display. And constructing a visual driving risk assessment result display platform. And when the system is triggered, the system emergency response probability and the historical driving behavior parameters of the driver are statistically and visually displayed, so that comprehensive evaluation of the risk avoiding driving behavior and the emergency disposal capability of the driver is facilitated.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims.
Claims (5)
1. An automatic emergency braking system that considers risk of collision, comprising: the system comprises a vehicle running state acquisition device, a road environment state acquisition device, a control decision device, an information storage device, an early warning device and a brake control device, and is characterized in that the vehicle running state acquisition device is selected from a speed sensor, an acceleration sensor and a distance measuring sensor and is mainly used for acquiring the current speed of a self-vehicle, the deceleration of the vehicle, the vehicle distance between the self-vehicle and a front workshop and the relative speed data of the self-vehicle and the front vehicle; the road environment state acquisition device is mainly used for acquiring road surface adhesion coefficients and road gradients; the control decision device selects a singlechip and controls an automatic emergency braking system through a vehicle collision risk prediction model; the information storage device is a memory that can read and write data; the early warning device selects a loudspeaker; the brake control device is connected with a vehicle brake control system;
the vehicle running state acquisition device and the road environment state acquisition device transmit detected data information to the control decision device, the control decision device receives the vehicle running state and road environment state data, makes a control decision based on the automatic emergency braking system considering collision risk, transmits decision information to the information storage device, the early warning device and the braking control device, the information storage device receives the decision information of the control decision device to write or read corresponding data, the early warning device receives the decision information of the control decision device to correspondingly warn a driver, and the braking control device is connected with the vehicle braking control system and is used for receiving the decision information of the control decision device to forcedly brake a vehicle;
the control decision device calculates the starting early warning of the vehicle and the moment of starting forced braking intervention risk avoidance by the following method:
the control decision device obtains the maximum braking deceleration which can be adopted by the current vehicle running road based on the road environment state parameters, meanwhile, the control decision device receives vehicle running parameter data, calculates and obtains an early warning critical distance threshold between a front vehicle and a self vehicle based on the following formula, when the relative distance between the self vehicle and the front vehicle is smaller than or equal to the calculated early warning critical distance threshold, the control decision device makes an early warning decision and transmits the early warning decision to the early warning device, the early warning device receives early warning decision information and makes corresponding early warning reminding for a vehicle driver, wherein the front vehicle is a front vehicle which has the shortest relative distance with the self vehicle and runs on the same lane, and the early warning critical distance threshold calculation formula is as follows:
wherein d is the pre-warning critical distance between the front vehicle and the own vehicle, v is the current speed of the own vehicle, and τ=t+t r ，t r Delay time for the brake; t is the reaction time of the driver in seconds, and particularly the reaction time of the driver in dangerous situations can be measured based on a simulated driving device and the like before the driver drives the real vehicle, so that the Tfinal value is the measured reaction time of the driver, v rel The relative speed between the own vehicle and the front vehicle; d, d 0 For between two vehicles after stoppingThe minimum safe distance is 5m, when the speed of the own vehicle is larger than the speed of the front vehicle, the control decision device calculates a TTC value based on the running state parameters of the vehicle, and when the TTC value is larger than the early warning critical value T br When the decision device is controlled to output a 0 signal; when the TTC value is not greater than the early warning critical value T br When the decision device is controlled to output a 1 signal;
the control decision device is internally provided with a vehicle collision risk prediction model, the vehicle collision risk prediction model is constructed based on a rear-end collision accident data set and own vehicle running history data by using a binary logistic regression method, the vehicle speed of a collision accident of a vehicle is predicted based on the vehicle collision risk prediction model in combination with the vehicle relative distance, the vehicle speed is compared with the current vehicle speed of the own vehicle, and when the predicted vehicle speed is greater than the current vehicle speed of the own vehicle, the control decision device controls and outputs a 0 signal; when the predicted vehicle speed is less than or equal to the current vehicle speed of the own vehicle, the control decision device controls and outputs a 1 signal, a vehicle collision risk prediction model can be constructed by adopting a rear-end collision accident case in a deep accident investigation database in the initial stage of the system, the model is input into the control decision device, and the vehicle speed of the collision accident of the vehicle is predicted by combining the vehicle collision risk prediction model with the vehicle relative distance and the maximum deceleration of a driver;
distance-based early warning critical distance threshold d and time-based early warning critical value T br And predicting the speed of the vehicle collision risk, wherein the output results of the three early warning calculation modes are respectively two classification variables, m represents the accumulated sum of the decision results of the three early warning modes, the final output result of the control decision device is a multi-element classification result, the respective discrimination results are coupled and applied to the early warning decision of the early warning system based on the three early warning discrimination modes, the early warning decision result is transmitted to the early warning device, and the early warning device carries out corresponding early warning operation based on the final early warning decision instruction.
2. The automatic emergency braking system considering collision risk according to claim 1, wherein the control decision device is mainly used for receiving data transmitted by the vehicle running state acquisition device and the road environment state acquisition device, extracting data information in the information storage device, making corresponding decisions based on an automatic emergency braking algorithm and a calculation result of a vehicle collision risk prediction model, and transmitting decision information to the early warning device, the information storage device and a brake control device of the own vehicle;
the information storage device is mainly used for storing data information of the triggering system event so as to be extracted and used by a control decision device or a technician;
the early warning device is mainly used for receiving the decision information of the control decision device and adopting a corresponding early warning reminding mode;
the braking control device is used for receiving the decision information of the control decision device and deciding whether to take braking measures.
3. An automatic emergency braking system according to claim 1, wherein said control decision means calculates the maximum braking deceleration that can be taken on the current running road of the vehicle based on the road adhesion coefficient and the road gradient data according to the following formula:
a max ＝g(sinθ+μcosθ)
wherein a is max The maximum braking deceleration of the vehicle is g, g is gravitational acceleration, θ is road gradient, and μ is road surface adhesion coefficient.
4. An automatic emergency braking system according to claim 1, wherein said TTC and said pre-warning threshold T br The calculation mode of (a) is as follows:
wherein d rel The relative distance between the vehicle and the front vehicle, u is repairPositive coefficients.
5. The method for evaluating the safety of an automatic emergency braking system taking collision risk into consideration according to any one of claims 1 to 4, wherein the specific early warning implementation of the system comprises the following steps:
the specific early warning implementation mode of the system is as follows:
(1) When f (x) =0, the system does not make early warning and braking operations, and does not interfere with the driving behavior of the driver and the running state of the vehicle;
(2) When f (x) =1, the early warning device triggers and activates and reminds a driver to pay attention to control the vehicle speed, so that rear-end collision accidents are prevented;
(3) When f (x) =2, the early warning device triggers activation and reminds a driver of carrying out emergency deceleration operation;
when the own vehicle continues to approach the front vehicle, the control decision device calculates a system braking critical distance threshold value based on the following formula, and dbr1 and dbr2 are respectively calculated and compared with the current distance of the vehicle, and the braking critical distance d is calculated br The calculation method is as follows:
d br1 ＝v rel τ+0.5a max τ 2
d br2 ＝TTC*v rel +d 0
the calculated output result of the braking critical distance is a binary variable 0 or 1, and when the relative distance between the own vehicle and the front vehicle is smaller than or equal to the calculated braking critical distance, the output result is 1; when the relative distance between the vehicle and the front vehicle is greater than the calculated braking critical distance, the output result is 0, the judging result is coupled and applied to the forced braking decision of the system based on two judging modes, s represents the sum of the two judging output results, and the final braking decision is implemented as follows:
when g (x) =0, the system does not perform forced braking intervention, and when g (x) =1, the control decision device makes forced braking decision and transmits the braking decision to the braking control device, and the braking control device receives braking decision information and immediately performs forced braking on the own vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111387055.9A CN114148321B (en) | 2021-11-22 | 2021-11-22 | Automatic emergency braking and safety evaluation method considering collision risk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111387055.9A CN114148321B (en) | 2021-11-22 | 2021-11-22 | Automatic emergency braking and safety evaluation method considering collision risk |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114148321A CN114148321A (en) | 2022-03-08 |
| CN114148321B true CN114148321B (en) | 2023-06-20 |
Family
ID=80457163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111387055.9A Active CN114148321B (en) | 2021-11-22 | 2021-11-22 | Automatic emergency braking and safety evaluation method considering collision risk |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114148321B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114863698B (en) * | 2022-05-12 | 2023-11-17 | 交通运输部公路科学研究所 | Active collision accident prevention and control system and method based on vehicle-road cooperation |
| CN116061913B (en) * | 2023-03-02 | 2023-06-30 | 青岛慧拓智能机器有限公司 | Underground vehicle rear-end collision prevention system based on self-adaptive PID control and control method |
| CN116461513B (en) * | 2023-06-16 | 2023-09-22 | 中国第一汽车股份有限公司 | Vehicle and collision early warning method thereof |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005126060A (en) * | 2003-09-30 | 2005-05-19 | Autoliv Development Ab | Apparatus for judging danger of rear end collision |
| DE102004048868A1 (en) * | 2004-10-07 | 2006-04-13 | Daimlerchrysler Ag | Method for detecting rear-end crash situations |
| CN102745194A (en) * | 2012-06-19 | 2012-10-24 | 东南大学 | Self-adaption alarming method for preventing tailgating with front car on expressway |
| CN107738644A (en) * | 2017-09-30 | 2018-02-27 | 长安大学 | A kind of vehicle control of collision avoidance method |
| CN107958269A (en) * | 2017-11-28 | 2018-04-24 | 江苏大学 | A kind of driving risk factor Forecasting Methodology based on hidden Markov model |
| CN109080604A (en) * | 2018-08-14 | 2018-12-25 | 格陆博科技有限公司 | A kind of automatic emergency brake system based on AEB system |
| CN109660967A (en) * | 2019-02-18 | 2019-04-19 | 华东交通大学 | A kind of driving safety monitoring apparatus and method based on the fusion of car networking BSM information |
| CN110097783A (en) * | 2019-05-15 | 2019-08-06 | 芜湖汽车前瞻技术研究院有限公司 | Vehicle early warning method and system |
| CN111994073A (en) * | 2020-07-22 | 2020-11-27 | 北京交通大学 | Automatic emergency braking control method |
| CN113538896A (en) * | 2021-04-20 | 2021-10-22 | 清华大学 | Critical driving condition analysis method and vehicle safety driving prompt system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011140993A1 (en) * | 2010-05-12 | 2011-11-17 | 北京星河易达科技有限公司 | Intelligent traffic safety system based on comprehensive state detection and decision method thereof |
-
2021
- 2021-11-22 CN CN202111387055.9A patent/CN114148321B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005126060A (en) * | 2003-09-30 | 2005-05-19 | Autoliv Development Ab | Apparatus for judging danger of rear end collision |
| DE102004048868A1 (en) * | 2004-10-07 | 2006-04-13 | Daimlerchrysler Ag | Method for detecting rear-end crash situations |
| CN102745194A (en) * | 2012-06-19 | 2012-10-24 | 东南大学 | Self-adaption alarming method for preventing tailgating with front car on expressway |
| CN107738644A (en) * | 2017-09-30 | 2018-02-27 | 长安大学 | A kind of vehicle control of collision avoidance method |
| CN107958269A (en) * | 2017-11-28 | 2018-04-24 | 江苏大学 | A kind of driving risk factor Forecasting Methodology based on hidden Markov model |
| CN109080604A (en) * | 2018-08-14 | 2018-12-25 | 格陆博科技有限公司 | A kind of automatic emergency brake system based on AEB system |
| CN109660967A (en) * | 2019-02-18 | 2019-04-19 | 华东交通大学 | A kind of driving safety monitoring apparatus and method based on the fusion of car networking BSM information |
| CN110097783A (en) * | 2019-05-15 | 2019-08-06 | 芜湖汽车前瞻技术研究院有限公司 | Vehicle early warning method and system |
| CN111994073A (en) * | 2020-07-22 | 2020-11-27 | 北京交通大学 | Automatic emergency braking control method |
| CN113538896A (en) * | 2021-04-20 | 2021-10-22 | 清华大学 | Critical driving condition analysis method and vehicle safety driving prompt system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114148321A (en) | 2022-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114148321B (en) | Automatic emergency braking and safety evaluation method considering collision risk | |
| CN112673407B (en) | System and method for predictive vehicle accident warning and avoidance | |
| US6734799B2 (en) | Apparatus and method for responding to the health and fitness of a driver of a vehicle | |
| US6871145B2 (en) | Method and system for vehicle impact assessment using driver braking estimation | |
| CN110329249B (en) | Automobile forward collision early warning control system and method of cyclic neural network | |
| Xiong et al. | Drivers' adaptation to adaptive cruise control: Examination of automatic and manual braking | |
| CN102303606B (en) | Hazard assessment method based on retarded velocity required by vehicle | |
| CN105501220A (en) | Vehicle collision warning method and device and vehicle | |
| US20210049908A1 (en) | Utilizing sensors to detect hazard from other vehicle while driving | |
| US20070296564A1 (en) | Rear collision warning system | |
| US20080183360A1 (en) | Vehicle collision avoidance and warning | |
| US7551991B2 (en) | Vehicle over speed indicator | |
| CN111038502A (en) | Safe vehicle distance pre-estimation, correction, early warning and driving qualification evaluation method and system | |
| CN111768651B (en) | Early warning method and device for preventing vehicle collision | |
| CN110517522B (en) | Vehicle speed limiting system and method for remote control | |
| CN113658451B (en) | Vehicle collision early warning control method and device, vehicle and readable storage medium | |
| CN106627590A (en) | Braking distance calculation method and device | |
| KR101521118B1 (en) | Driver-customized automotive active safety system | |
| CN113165615A (en) | Vehicle control method and device | |
| CN114987502B (en) | Driving state monitoring method and device, computer equipment and storage medium | |
| CN117022323A (en) | Intelligent driving vehicle behavior analysis and prediction system and method | |
| CN111856510A (en) | Vehicle front collision prediction method based on laser radar | |
| EP3133573A1 (en) | System and method for collision warning | |
| CN114613131B (en) | Safety margin-based personalized forward collision early warning method | |
| CN109927729B (en) | Method and device for estimating safe distance of continuous high-speed driving and evaluating and controlling stability |
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 |