CN115009274A - Intelligent networking automobile risk assessment method and personalized decision-making method - Google Patents

Intelligent networking automobile risk assessment method and personalized decision-making method Download PDF

Info

Publication number
CN115009274A
CN115009274A CN202210754129.6A CN202210754129A CN115009274A CN 115009274 A CN115009274 A CN 115009274A CN 202210754129 A CN202210754129 A CN 202210754129A CN 115009274 A CN115009274 A CN 115009274A
Authority
CN
China
Prior art keywords
risk
vehicle
driving
surrounding vehicle
surrounding
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210754129.6A
Other languages
Chinese (zh)
Inventor
孙栋先
郭宏伟
王武宏
蒋晓蓓
石健
谭海秋
张浩东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Technology BIT
Original Assignee
Beijing Institute of Technology BIT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Technology BIT filed Critical Beijing Institute of Technology BIT
Priority to CN202210754129.6A priority Critical patent/CN115009274A/en
Publication of CN115009274A publication Critical patent/CN115009274A/en
Pending legal-status Critical Current

Links

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
    • B60W30/095—Predicting travel path or likelihood of collision
    • B60W30/0953—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic parameters
    • 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
    • B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • B60W2520/105—Longitudinal acceleration
    • 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
    • B60W2530/00—Input parameters relating to vehicle conditions or values, not covered by groups B60W2510/00 or B60W2520/00
    • B60W2530/10—Weight

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses an intelligent networking automobile risk assessment method and an individualized decision method, which comprise the following steps: respectively calculating driving risks of the surrounding vehicles to the main vehicle by using a driving safety field model according to the main vehicle data and the surrounding vehicle data; respectively weighting and calculating the following risk and the lane changing risk of the main vehicle according to the driving risk of each surrounding vehicle to the main vehicle; selecting a driving style, and comparing the driving risk borne by the main vehicle with a driving risk threshold value corresponding to the driving style respectively so as to determine the driving state of the main vehicle; the invention has accurate driving risk assessment and comprehensive risk consideration dimension and can meet the comfort requirements of different types of drivers or passengers.

Description

Intelligent networking automobile risk assessment method and personalized decision-making method
Technical Field
The invention belongs to the technical field of automobile driving decision, and particularly relates to an intelligent networked automobile risk assessment method and an individualized decision method.
Background
The intelligent internet automobile based on the new generation communication technology can effectively solve the technical bottleneck faced by the single-automobile automatic driving, and is a hotspot of the current automatic driving and intelligent traffic field research. The intelligent decision is used as an important component module of the intelligent networked automobile, and has important influence on the safe driving of the automobile and the road traffic safety. How to effectively evaluate the driving risk formed by surrounding traffic participants in a complex driving scene so as to make a reasonable and effective decision is one of the key problems faced by the current intelligent networked automobile.
In the existing vehicle intelligent decision-making research based on driving risk assessment, the driving risk is assessed only by considering the speed and distance factors between a main vehicle and surrounding vehicles, and evaluating indexes such as collision time, head time and the like. However, this decision method has certain problems: firstly, when driving risk assessment is carried out, the considered influence factors are less, so that the risk assessment result is inaccurate; secondly, only longitudinal or transverse single-dimension driving risks are considered, and the risk assessment dimension is single; thirdly, different types of drivers or passengers have different driving risk psychological thresholds, and vehicle intelligent decision making is performed based on the same driving risk criterion, so that the requirements of the drivers or passengers on driving comfort cannot be met.
Therefore, the existing vehicle intelligent decision-making method based on risk assessment and the related technology are difficult to meet the development requirements of intelligent networked automobiles.
Disclosure of Invention
In view of the above, the invention provides an intelligent networked automobile risk assessment method and an individualized decision method, so that driving risk assessment is accurate, risk consideration dimensionality is comprehensive, and comfort requirements of drivers or passengers of different types can be met.
The invention is realized by the following technical scheme:
an intelligent networked automobile risk assessment method comprises the following steps: according to data for driving risk assessment acquired by a sensor of intelligent networked vehicle equipment and a vehicle path cooperative sensing facility in an intelligent networked environment, wherein the data comprises main vehicle data and surrounding vehicle data, driving risks of surrounding vehicles on a main vehicle are calculated respectively by using a driving safety field model;
wherein the host vehicle data comprises physical mass, transverse coordinates, longitudinal coordinates, velocity, and acceleration of the host vehicle; the surrounding vehicle data includes the physical mass, lateral coordinates, longitudinal coordinates, length, width, speed, and acceleration of each surrounding vehicle.
Furthermore, according to driving risks of surrounding vehicles to the main vehicle, the following risks and the lane changing risks of the main vehicle are calculated in a weighted mode respectively.
Further, the manner of respectively calculating the driving risks of the surrounding vehicles to the main vehicle by using the driving safety field model is as follows:
step S11, calculating the risk quality of a surrounding vehicle A according to the physical quality and speed of the surrounding vehicle A;
step S12, on one hand, calculating the potential energy risk field strength of the surrounding vehicle A by combining the risk quality of the surrounding vehicle A with the transverse coordinate and the longitudinal coordinate of the main vehicle and the transverse coordinate, the longitudinal coordinate, the length and the width of the surrounding vehicle A; on the other hand, the risk quality of the surrounding vehicle A is combined with the transverse coordinate and the longitudinal coordinate of the main vehicle and the transverse coordinate, the longitudinal coordinate, the length, the width and the speed of the surrounding vehicle A to calculate the kinetic energy risk field strength of the surrounding vehicle A;
step S13, combining the potential energy risk field intensity and the kinetic energy risk field intensity of the surrounding vehicle A obtained in the step S12 to obtain the risk field intensity of the surrounding vehicle A;
step S14, calculating the driving risk of the surrounding vehicle A to the host vehicle by combining the physical mass, the speed and the acceleration of the host vehicle and the speed of the surrounding vehicle A according to the risk field intensity of the surrounding vehicle A obtained in the step S13;
and step S15, calculating the driving risks of the surrounding vehicles to the host vehicle according to the steps S11-S14 respectively.
Further, in step S12, the calculation formula of the potential energy risk field strength of the surrounding vehicle a obtained by combining the lateral coordinate and the longitudinal coordinate of the host vehicle and the lateral coordinate, the longitudinal coordinate, the length and the width of the surrounding vehicle a is as follows:
Figure BDA0003719188030000021
wherein E is sv_sta Potential energy risk field strength of surrounding vehicles A, A is a field strength coefficient greater than 0, M sv Is the risk quality, x, of the surrounding vehicle A obtained in step S11 ev As principal longitudinal coordinate, x sv Is the longitudinal coordinate of the surrounding vehicle A, w x Weight coefficient for the length of surrounding vehicle A, L sv Is the length of the surrounding vehicle A, y ev As longitudinal coordinate of the principal vehicle, y sv Is the lateral coordinate of the surrounding vehicle A, w y Weight coefficient, W, for the width of the surrounding vehicle A sv Is the width of the surrounding vehicle a, d is the distance vector between the host vehicle and the surrounding vehicle a, d ═ x ev -x sv ,y ev -y sv )。
Further, in step S12, the calculation formula of the kinetic energy risk field strength of the surrounding vehicle a obtained by combining the lateral coordinate and the longitudinal coordinate of the host vehicle and the lateral coordinate, the longitudinal coordinate, the length, the width and the velocity of the surrounding vehicle a is as follows:
Figure BDA0003719188030000022
wherein, E sv_va The kinetic energy risk field strength of a surrounding vehicle A, A being a field strength coefficient greater than 0, M sv Is the risk quality, x, of the surrounding vehicle A obtained in step S11 ev As principal longitudinal coordinate, x sv Is the longitudinal coordinate of the surrounding vehicle A, alpha is a weight coefficient related to the speed of the surrounding vehicle A, v sv Speed of the surrounding vehicle A, w x Weight coefficient for the length of surrounding vehicle A, L sv Is the length of the surrounding vehicle A, y ev As longitudinal coordinate of the principal vehicle, y sv Is the lateral coordinate of the surrounding vehicle A, w y Weight coefficient, W, for the width of the surrounding vehicle A sv For surrounding vehiclesThe width of the vehicle A, theta is an included angle between the speed direction of the vehicle A around and d, and the clockwise direction is positive; gamma is a weight coefficient related to the included angle theta; beta is a weight coefficient related to the acceleration of the surrounding vehicle A, a sv D is the acceleration of a certain surrounding vehicle A, d is the distance vector between the host vehicle and the surrounding vehicle A, and d is (x) ev -x sv ,y ev -y sv )。
Further, the calculation formula of step S14 is:
Figure BDA0003719188030000031
wherein r is ev Driving risk to the host vehicle for the surrounding vehicle A, E sv The risk field intensity, m, of the surrounding vehicle A obtained in step S13 ev Is the physical mass of the master vehicle; w is a v Is the relative velocity | v of the host vehicle and the surrounding vehicle A ev -v sv A weight coefficient of | is; v. of ev Is the host vehicle speed; v. of sv A certain surrounding vehicle speed; w is a a A weight coefficient that is a principal acceleration; a is a ev The principal acceleration is.
Further, the following risk suffered by the main vehicle is calculated according to the driving risk generated by the front surrounding vehicle, the left front surrounding vehicle and the right front surrounding vehicle on the main vehicle in a weighted mode;
and calculating the lane change risk of the main vehicle according to the driving risk generated by the left front surrounding vehicle, the left rear surrounding vehicle, the right front surrounding vehicle and the right rear surrounding vehicle on the main vehicle.
An intelligent networked automobile personalized decision-making method based on the intelligent networked automobile risk assessment method comprises the following steps: and selecting a driving style, and comparing the driving risk borne by the main vehicle with a driving risk threshold value corresponding to the driving style respectively so as to determine the driving state of the main vehicle.
Further, the driving risk comprises a following risk and a lane changing risk, and the driving risk threshold comprises a following risk threshold and a lane changing risk threshold;
comparing the driving risk borne by the main vehicle with a driving risk threshold corresponding to the driving style, so as to determine the driving state of the main vehicle in the following mode:
when the following risk of the main vehicle is less than or equal to the following risk threshold value, the main vehicle normally runs;
when the following risk of the main vehicle is greater than the following risk threshold value, the left and right lane changing risks of the main vehicle are respectively compared with the lane changing risk threshold value corresponding to the driving style, and the following four conditions are adopted:
if the left lane changing risk and the right lane changing risk are both smaller than or equal to the lane changing risk threshold value, the main lane changes the lane on the left side or the lane on the right side;
if the left lane change risk is less than or equal to the lane change risk threshold and the right lane change risk is greater than the lane change risk threshold, the primary vehicle performs left lane change;
if the lane change risk on the left side is greater than the lane change risk threshold value and the lane change risk on the right side is less than or equal to the lane change risk threshold value, the main vehicle performs the lane change on the right side;
and if the left lane changing risk and the right lane changing risk are both greater than or equal to the lane changing risk threshold, the main vehicle executes braking.
Further, the following risk threshold and lane change risk threshold are determined in the following manner: based on the public natural driving data set, the following risk and the lane changing risk of a driver under the real road driving condition are clustered and analyzed, the driving risk and the lane changing risk are divided into three classes, and the clustering centers of the three classes are respectively and correspondingly used as the following risk threshold and the lane changing risk threshold of aggressive, normal and conservative driving styles.
Has the advantages that:
(1) the data of the main vehicle comprises the physical mass, the transverse coordinate, the longitudinal coordinate, the speed and the acceleration of the main vehicle; the surrounding vehicle data includes the physical mass, lateral coordinates, longitudinal coordinates, length, width, velocity, and acceleration of each surrounding vehicle. The invention takes the driving safety field model as the basis, comprehensively considers the physical mass, the transverse coordinate, the longitudinal coordinate, the speed and the acceleration of the main vehicle and the physical mass, the transverse coordinate, the longitudinal coordinate, the length, the width, the speed, the acceleration, the course angle and other factors of the surrounding vehicles, thereby accurately calculating the driving risk of the surrounding vehicles to the main vehicle.
(2) According to the driving risks of surrounding vehicles to the main vehicle, the following risks and the lane changing risks borne by the main vehicle are calculated in a weighted mode respectively. According to the invention, the driving risk caused by the surrounding vehicles of the single vehicle is weighted and calculated, the longitudinal following risk and the transverse lane changing risk of the main vehicle are obtained, the driving risk of the transverse dimension and the longitudinal dimension is comprehensively considered, and the driving safety is further ensured.
(3) According to the invention, the potential energy risk field strength of the surrounding vehicle A is calculated by combining the risk quality of the surrounding vehicle A with the transverse coordinate and the longitudinal coordinate of the main vehicle and the transverse coordinate, the longitudinal coordinate, the length and the width of the surrounding vehicle A. In reality, the larger the vehicle size is, the larger the risk generated by the vehicle is, and the vehicle has different influences on different directions.
(4) The kinetic energy risk field intensity of the surrounding vehicle A is calculated by combining the risk quality of the surrounding vehicle A with the transverse coordinate and the longitudinal coordinate of the main vehicle and the transverse coordinate, the longitudinal coordinate, the length, the width and the speed of the surrounding vehicle A. Besides the introduction of the vehicle geometric attributes for calculation, the peripheral vehicle speed is introduced into the kinetic energy field model in consideration of the fact that the peripheral vehicle speed has different influences on the transverse direction and the longitudinal direction, so that the influences of the peripheral vehicle speed on the transverse direction and the longitudinal direction in different directions are calculated, and the accuracy of calculation of the kinetic energy risk field strength of the peripheral vehicle is further improved.
(5) According to the risk field intensity of the surrounding vehicle A obtained in the step S13, the driving risk of the surrounding vehicle A to the host vehicle is calculated by combining the physical mass, the speed and the acceleration of the host vehicle and the speed of the surrounding vehicle A, and the relative speed of the vehicle and the acceleration of the host vehicle are introduced into a final driving risk calculation formula of the surrounding vehicle to the host vehicle by considering that the risk of the host vehicle is related to the relative speeds of the two vehicles, but not only to the speed of the host vehicle, so that the accuracy of risk evaluation is further improved.
(6) According to the driving risk generated by the front surrounding vehicles, the left front surrounding vehicles and the right front surrounding vehicles on the main vehicle, the following risk borne by the main vehicle is calculated in a weighted mode; and calculating the lane change risk of the main vehicle according to the driving risk generated by the left front surrounding vehicle, the left rear surrounding vehicle, the right front surrounding vehicle and the right rear surrounding vehicle on the main vehicle. Because the magnitude of the following risk experienced by the host vehicle is mainly affected by the preceding surrounding vehicles, the left preceding surrounding vehicle, and the right preceding surrounding vehicle, there is no need to consider the driving risk of other surrounding vehicles on the host vehicle; because the main vehicle is subjected to the lane changing risk, the numerical value of the main vehicle is mainly influenced by vehicles in adjacent lanes of the main vehicle, and the driving risk of the vehicles around the front to the main vehicle does not need to be considered.
(7) According to the invention, the driving style is selected, and the driving risk suffered by the main vehicle is compared with the driving risk threshold value corresponding to the driving style, so that the driving state of the main vehicle is determined. According to the invention, after the driver or the passenger selects the driving style, the corresponding threshold value is compared and judged with the driving risk of the main vehicle, and then the driving state of the main vehicle is determined, so that the personalized intelligent decision of the vehicle is realized, and the decision meets the requirement of the driver or the passenger on the comfortable driving style.
(8) The driving risk suffered by the main vehicle is compared with the driving risk threshold value corresponding to the driving style, so that the driving state of the main vehicle is determined in the following mode: when the following risk of the main vehicle is less than or equal to the following risk threshold value, the main vehicle normally runs; when the following risk of the main vehicle is greater than the following risk threshold value, the left and right lane changing risks of the main vehicle are respectively compared with the lane changing risk threshold value corresponding to the driving style, and the following four conditions are adopted: if the left lane changing risk and the right lane changing risk are both smaller than or equal to the lane changing risk threshold value, the main lane changes the lane on the left side or the lane on the right side; if the left lane change risk is less than or equal to the lane change risk threshold and the right lane change risk is greater than the lane change risk threshold, the primary vehicle performs left lane change; if the lane change risk on the left side is greater than the lane change risk threshold value and the lane change risk on the right side is less than or equal to the lane change risk threshold value, the main vehicle performs the lane change on the right side; and if the left lane changing risk and the right lane changing risk are both greater than or equal to the lane changing risk threshold, the main vehicle executes braking. The invention firstly compares the following risks and then compares the lane changing risks, thereby ensuring the driving safety of the main vehicle while ensuring the personalized decision.
(9) The invention is based on a public natural driving data set, the following risk and the lane changing risk under the real road driving condition of a driver are clustered and analyzed, the following risk and the lane changing risk are divided into three classes, and the clustering centers of the three classes of clusters are respectively and correspondingly used as the following risk threshold and the lane changing risk threshold of aggressive, normal and conservative driving styles. The clustering analysis can also be free from the limitation of three types, and the types can be further divided, so that the requirements of different driving styles are met.
Drawings
FIG. 1 is a frame diagram of an intelligent networked automobile personalized decision making based on multi-dimensional risk assessment provided by the present invention;
FIG. 2 is a schematic view of the distribution of vehicles around the present invention;
FIG. 3 is a flow chart of the vehicle personalized intelligent decision making process of the present invention.
Detailed Description
The invention is described in detail below by way of example with reference to the accompanying drawings.
Example 1:
the embodiment provides an intelligent networking automobile risk assessment method, referring to fig. 1, including: according to data for driving risk assessment acquired by a sensor of intelligent networked vehicle equipment and a vehicle path cooperative sensing facility in an intelligent networked environment, wherein the data comprises main vehicle data and surrounding vehicle data, driving risks of surrounding vehicles on a main vehicle are calculated respectively by using a driving safety field model; wherein the host vehicle data comprises physical mass, transverse coordinates, longitudinal coordinates, velocity, and acceleration of the host vehicle; the surrounding vehicle data includes the physical mass, lateral coordinates, longitudinal coordinates, length, width, velocity, and acceleration of each surrounding vehicle.
In the embodiment, on the basis of a driving safety field model, the physical mass, the transverse coordinate, the longitudinal coordinate, the speed and the acceleration of the main vehicle and the physical mass, the transverse coordinate, the longitudinal coordinate, the length, the width, the speed, the acceleration, the course angle and other factors of surrounding vehicles are comprehensively considered, so that the driving risk of each surrounding vehicle on the main vehicle is accurately calculated.
Further, referring to fig. 2, the surrounding vehicle includes: front surrounding vehicles, a left front surrounding vehicle, a left rear surrounding vehicle, a right front surrounding vehicle and a right rear surrounding vehicle, wherein the maximum number of the surrounding vehicles is 5, and the minimum number of the surrounding vehicles is 0;
front surrounding vehicle f v A vehicle with the smallest longitudinal distance and located in the front 120m of the lane where the host vehicle is located;
left front surrounding vehicle lf v A vehicle with the smallest longitudinal distance and located within 120m of the left adjacent lane of the host vehicle;
left rear surrounding vehicle lr v A vehicle with the smallest longitudinal distance and located within 120m behind the adjacent lane on the left side of the host vehicle;
right front surrounding vehicle rf v A vehicle defined as the vehicle located within 120m in front of the adjacent lane on the right side of the host vehicle, the longitudinal distance of which is the smallest;
right rear surrounding vehicle rr v And is defined as the vehicle with the smallest longitudinal distance, which is located in the rear 120m of the adjacent lane on the right side of the host vehicle.
Further, the mode of respectively calculating the driving risks of the surrounding vehicles to the main vehicle by using the driving safety field model is as follows:
step S11, calculating the risk mass of a surrounding vehicle a according to the physical mass and speed of the surrounding vehicle a, according to the following formula:
Figure BDA0003719188030000061
wherein M is sv For the risk mass of the surrounding vehicle A, m sv Is the physical mass of the surrounding vehicle A, v sv Is the speed of the surrounding vehicle a;
step S12, on one hand, the risk quality of the surrounding vehicle a is calculated by combining the lateral coordinate and the longitudinal coordinate of the host vehicle and the lateral coordinate, the longitudinal coordinate, the length and the width of the surrounding vehicle a to obtain the potential energy risk field strength of the surrounding vehicle a, and the calculation formula is as follows:
Figure BDA0003719188030000071
wherein E is sv_sta Potential energy risk field strength of surrounding vehicles A, A is a field strength coefficient larger than 0, M sv Is the risk quality, x, of the surrounding vehicle A obtained in step S11 ev As principal longitudinal coordinate, x sv Is the longitudinal coordinate of the surrounding vehicle A, w x Weight coefficient for the length of surrounding vehicle A, L sv Is the length of the surrounding vehicle A, y ev As longitudinal coordinate of the principal vehicle, y sv Is the lateral coordinate of the surrounding vehicle A, w y Weight coefficient, W, for the width of the surrounding vehicle A sv Is the width of the surrounding vehicle a, d is the distance vector between the host vehicle and the surrounding vehicle a, d ═ x ev -x sv ,y ev -y sv )；
On the other hand, the risk quality of the surrounding vehicle a is combined with the transverse coordinate and the longitudinal coordinate of the host vehicle and the transverse coordinate, the longitudinal coordinate, the length, the width and the speed of the surrounding vehicle a to calculate the kinetic energy risk field strength of the surrounding vehicle a, and the calculation formula is as follows:
Figure BDA0003719188030000072
wherein E is sv_va Is the kinetic energy risk field strength of the surrounding vehicle A, alpha is a weight coefficient related to the velocity of the surrounding vehicle A, v sv Is the speed of the surrounding vehicle a; theta is an included angle between the speed direction of a surrounding vehicle A and d, and the clockwise direction is positive; gamma is a weight coefficient related to the included angle theta; beta is a weight coefficient related to the acceleration of the surrounding vehicle A, a sv Acceleration of a certain surrounding vehicle a;
step S13, combining the potential energy risk field strength and the kinetic energy risk field strength of the surrounding vehicle a obtained in step S12 to obtain the risk field strength of the surrounding vehicle a, and the calculation formula is as follows:
E sv ＝E sv_sta +E sv_va formula (4)
Wherein E is sv At risk field strength of a certain surrounding vehicle A, E sv_sta Potential energy risk field strength, E, of the surrounding vehicle A obtained in step S12 sv_va The kinetic energy risk field strength of the surrounding vehicle a obtained in step S12;
step S14, calculating the driving risk of the surrounding vehicle A to the host vehicle by combining the physical mass, the speed and the acceleration of the host vehicle and the speed of the surrounding vehicle A according to the risk field intensity of the surrounding vehicle A obtained in step S13, wherein the calculation formula is as follows:
Figure BDA0003719188030000073
wherein r is ev Driving risk to the host vehicle for the surrounding vehicle A, E sv The risk field intensity, m, of the surrounding vehicle A obtained in step S13 ev Is the physical mass of the master vehicle; w is a v Is the relative velocity | v of the host vehicle and the surrounding vehicle A ev -v sv A weight coefficient of |; v. of ev Is the host vehicle speed; v. of sv A certain surrounding vehicle speed; w is a a A weight coefficient that is a principal acceleration; a is ev The principal acceleration is.
And step S15, respectively calculating the driving risks of the surrounding vehicles to the host vehicle according to the steps S11-S14 (namely the driving safety field model).
Further, the surrounding vehicle data further includes a heading angle of the surrounding vehicle, and when the heading angle of the surrounding vehicle a is not 0 °, the coordinates of the surrounding vehicle a need to be transformed, where the coordinate transformation formula is:
Figure BDA0003719188030000081
wherein, x' sv To change overLongitudinal coordinate of rear surrounding vehicle A, y' sv To the transformed lateral coordinates of the surrounding vehicle a,
Figure BDA0003719188030000082
is the heading angle of the surrounding vehicle a, and is positive counterclockwise.
Converting the coordinates x 'of the surrounding vehicle A' sv 、y' sv Respectively replacing the coordinates x of the original surrounding vehicle A sv ，y sv And (6) performing calculation.
In the actual driving environment, the heading angle of the vehicle is not 0 degree, for example, in a lane-changing cut-in scene, the vehicle body is not parallel to the road direction, and at the moment, the risk field of the moving vehicle needs to deflect at a certain angle, so that the driving risk of the surrounding vehicle to the main vehicle is more accurately described.
Example 2:
in another embodiment of the present application, a method for evaluating risk of an intelligent networked automobile, referring to fig. 1, further includes: and respectively weighting and calculating the following risk and the lane changing risk of the main vehicle according to the driving risk of each surrounding vehicle to the main vehicle.
In the embodiment, the driving risk caused by the surrounding vehicles of the single vehicle is subjected to weighted calculation, the longitudinal following risk and the transverse lane changing risk of the main vehicle are obtained, the driving risk of the transverse dimension and the longitudinal dimension is comprehensively considered, and the driving safety is further ensured.
Further, because the magnitude of the following risk suffered by the host vehicle is mainly influenced by the front surrounding vehicle, the left front surrounding vehicle and the right front surrounding vehicle, the following risk suffered by the host vehicle is calculated according to the driving risk weight of the front surrounding vehicle, the left front surrounding vehicle and the right front surrounding vehicle on the host vehicle, and the specific calculation method is as follows:
r cf ＝w lf r sv_lf +w mf r sv_mf +w rf r sv_rf formula (7)
Wherein r is cf The following risk of the main vehicle, w lf Driving risk weight coefficient, r, for the left front surrounding vehicle sv_lf Is the left frontDriving risk of surrounding vehicles to the host vehicle, w mf Driving risk weight coefficient, r, for surrounding vehicles ahead sv_mf Driving risk to the host vehicle for surrounding vehicles ahead, w rf Driving risk weight coefficient, r, for the right front surrounding vehicle sv_rf Driving risk to the host vehicle for a vehicle around the right front;
further, because the main vehicle is subjected to the lane change risk, the numerical value of the lane change risk is mainly influenced by the vehicles in the adjacent lanes of the main vehicle, the lane change risk of the main vehicle is calculated according to the driving risk generated by the vehicles around the left front, the vehicles around the left rear, the vehicles around the right front and the vehicles around the right rear to the main vehicle, and the specific calculation method comprises the following steps:
Figure BDA0003719188030000083
wherein r is lc_l The lane change risk faced by the left lane of the main vehicle, w lf Driving risk weight coefficient, r, for the left front surrounding vehicle sv_lf Driving risk to the host vehicle for the surrounding vehicles in front of the left, w lr Driving risk weight coefficient, r, for the left rear surrounding vehicle sv_lr Driving risks to the host vehicle for vehicles around the left rear; r is lc_r The lane change risk for the right lane, w rf Driving risk weight coefficient, r, for the right front surrounding vehicle sv_rf Driving risk to the host vehicle for the right front surrounding vehicle, w rr Driving risk weight coefficient, r, for the right rear surrounding vehicle sv_rr A driving risk to the host vehicle is created for the right rear surrounding vehicle.
Example 3:
in another embodiment of the present application, an intelligent networked automobile personalized decision method is based on the intelligent networked automobile risk assessment method in embodiments 1 and 2, and with reference to fig. 1, the method includes: and selecting a driving style, and comparing the driving risk borne by the main vehicle with a driving risk threshold value corresponding to the driving style respectively so as to determine the driving state of the main vehicle.
According to the embodiment, after the driver or the passenger selects the driving style, the corresponding threshold value is compared and judged with the driving risk of the main vehicle, and the vehicle personalized intelligent decision considering the comfort of the driver or the passenger is realized.
Further, the driving risk comprises a following risk and a lane changing risk, and the driving risk threshold comprises a following risk threshold and a lane changing risk threshold;
referring to fig. 3, the driving risk experienced by the host vehicle is compared with a driving risk threshold corresponding to the driving style, so as to determine the driving state of the host vehicle in the following manner:
when the following risk of the main vehicle is less than or equal to the following risk threshold value, the main vehicle normally runs;
when the following risk of the main vehicle is greater than the following risk threshold value, the left and right lane changing risks of the main vehicle are respectively compared with the lane changing risk threshold value corresponding to the driving style, and the following four conditions are adopted:
if the left lane changing risk and the right lane changing risk are both smaller than or equal to the lane changing risk threshold value, the main lane changes the lane on the left side or the lane on the right side;
if the left lane change risk is less than or equal to the lane change risk threshold and the right lane change risk is greater than the lane change risk threshold, the primary vehicle performs left lane change;
if the lane change risk on the left side is greater than the lane change risk threshold value and the lane change risk on the right side is less than or equal to the lane change risk threshold value, the main vehicle performs the lane change on the right side;
and if the left lane changing risk and the right lane changing risk are both greater than or equal to the lane changing risk threshold, the main vehicle executes braking.
Further, the following risk threshold and the lane change risk threshold are determined in the following manner: based on the public natural driving data set, carrying out cluster analysis on the following risk and the lane changing risk of a driver under the real road driving condition, dividing the following risk and the lane changing risk into three classes, wherein the cluster centers of the three classes are respectively and correspondingly used as the following risk threshold value and the lane changing risk threshold value of aggressive, normal and conservative driving styles; the method comprises the following specific steps:
step S31: according to the existing public natural driving data set, the following risk of the driver under the real road driving condition is calculated by using formulas (1) - (7), namely the following risk of the driver at the initial lane changing time; calculating and obtaining the lane change risk under the real road driving condition of the driver by using the formulas (1) to (6) and (8), namely the lane change risk at the initial time when the driver performs the lane change
Step S32: inputting the following risk and the lane change risk under the real road driving condition of the driver obtained in the step S31 into a cluster analysis algorithm, setting the number of the cluster to 3, and defining the obtained centers of the three clusters as a following risk threshold and a lane change risk threshold corresponding to three driving styles of an aggressive driver, a normal driver and a conservative driver or a passenger respectively, specifically referring to table i:
TABLE 1 Risk thresholds for respective driving styles
Conserved form Normal type Radical type
Following risk threshold R cf R cf_c R cf_m R cf_r
Lane change risk threshold R lc R lc_c R lc_m R lc_r
Example 4:
in the embodiment of the application, based on the conservative driving style, the method is used for introducing an intelligent networked automobile risk assessment method and an individualized decision method in a one-way three-lane scene, and the method comprises the following specific steps:
the method comprises the following steps: under the environment of intelligent network connection, acquiring the physical quality, transverse coordinates, longitudinal coordinates, speed and acceleration of the main vehicle based on a sensor and a vehicle-road cooperative sensing facility of the equipment of the intelligent network-connected vehicle; physical mass, lateral coordinate, longitudinal coordinate, length, width, speed, acceleration, and heading angle of each surrounding vehicle;
step two: calculating the driving risk of each surrounding vehicle to the main vehicle according to the formulas (1) to (6);
step three: according to the driving risks of the surrounding vehicles to the main vehicle in the step two, on one hand, the following risk r borne by the main vehicle is obtained by combining weighted average calculation of a formula (7) cf (ii) a On the other hand, the weighted average calculation of the formula (8) is combined to obtain the lane change risk r faced by the left lane and the right lane of the main vehicle lc_l And r lc_r ；
Step four: the conservative following risk threshold is R cf_c The lane change risk threshold is R lc_c ；
The following risk r obtained in the step three is used cf The conservative following risk threshold is R cf_c And (3) comparison:
when the following risk of the host vehicle is less than or equal to the following risk threshold, namely r cf ≤R cf_c When the vehicle is running, the main vehicle drives normally;
when the following risk of the host vehicle is greater than the following risk threshold, i.e. r cf >R cf_c In time, the lane change risk r faced by the left and right lanes lc_l And r lc_r Respectively with a lane change risk threshold of R lc_c The comparison and judgment are divided into the following four cases:
if r lc_l ≤R lc_c Or r lc_r ≤R lc_c If the lane change is not performed, the main vehicle changes the lane to the left side or the right side;
if r is lc_l ≤R lc_c And r is lc_l >R lc_c If so, the main vehicle changes the lane to the left side;
if r lc_l >R lc_c And r is lc_r ≤R lc_c If so, changing the lane on one side of the main vehicle direction;
if r lc_l >R lc_c And r is lc_l >R lc_c The host vehicle performs braking.
In summary, the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. An intelligent networked automobile risk assessment method is characterized by comprising the following steps: according to data for driving risk assessment acquired by a sensor of intelligent networked vehicle equipment and a vehicle path cooperative sensing facility in an intelligent networked environment, wherein the data comprises main vehicle data and surrounding vehicle data, driving risks of surrounding vehicles on a main vehicle are calculated respectively by using a driving safety field model;
wherein the host vehicle data comprises physical mass, transverse coordinates, longitudinal coordinates, velocity, and acceleration of the host vehicle; the surrounding vehicle data includes the physical mass, lateral coordinates, longitudinal coordinates, length, width, velocity, and acceleration of each surrounding vehicle.
2. The intelligent networked automobile risk assessment method according to claim 1, wherein the following risk and the lane change risk suffered by the main automobile are weighted and calculated respectively according to the driving risk of each surrounding automobile to the main automobile.
3. The method as claimed in claim 1, wherein the driving risk of the vehicle generated by each surrounding vehicle to the host vehicle is calculated by using the driving safety field model by:
step S11, calculating the risk quality of a surrounding vehicle A according to the physical quality and speed of the surrounding vehicle A;
step S12, on one hand, calculating the potential energy risk field strength of the surrounding vehicle A by combining the risk quality of the surrounding vehicle A with the transverse coordinate and the longitudinal coordinate of the main vehicle and the transverse coordinate, the longitudinal coordinate, the length and the width of the surrounding vehicle A; on the other hand, the risk quality of the surrounding vehicle A is combined with the transverse coordinate and the longitudinal coordinate of the main vehicle and the transverse coordinate, the longitudinal coordinate, the length, the width and the speed of the surrounding vehicle A to calculate the kinetic energy risk field strength of the surrounding vehicle A;
step S13, combining the potential energy risk field intensity and the kinetic energy risk field intensity of the surrounding vehicle A obtained in the step S12 to obtain the risk field intensity of the surrounding vehicle A;
step S14, calculating the driving risk of the surrounding vehicle A to the host vehicle by combining the physical mass, the speed and the acceleration of the host vehicle and the speed of the surrounding vehicle A according to the risk field intensity of the surrounding vehicle A obtained in the step S13;
and step S15, calculating the driving risks of the surrounding vehicles to the host vehicle according to the steps S11-S14 respectively.
4. The intelligent networked automobile risk assessment method according to claim 3, wherein the risk quality of the surrounding vehicle A in step S12 is calculated by combining the lateral coordinate and the longitudinal coordinate of the main vehicle and the lateral coordinate, the longitudinal coordinate, the length and the width of the surrounding vehicle A to obtain the calculation formula of the potential energy risk field strength of the surrounding vehicle A, wherein the calculation formula is as follows:
Figure FDA0003719188020000011
wherein E is sv_sta Potential energy risk field strength of surrounding vehicles A, A is a field strength coefficient greater than 0, M sv Is the risk quality, x, of the surrounding vehicle A obtained in step S11 ev As principal longitudinal coordinate, x sv Is the longitudinal coordinate of the surrounding vehicle A, w x Weight coefficient, L, for the length of the surrounding vehicle A sv Is the length of the surrounding vehicle A, y ev As longitudinal coordinate of the principal vehicle, y sv Is the lateral coordinate of the surrounding vehicle A, w y Weight coefficient, W, for the width of the surrounding vehicle A sv Is the width of the surrounding vehicle a, d is the distance vector between the host vehicle and the surrounding vehicle a, d ═ x ev -x sv ,y ev -y sv )。
5. The method for risk assessment of intelligent networked automobiles according to claim 3 or 4, wherein the risk quality of the surrounding vehicle A in step S12 is calculated by combining the lateral coordinate and the longitudinal coordinate of the main automobile and the lateral coordinate, the longitudinal coordinate, the length, the width and the speed of the surrounding vehicle A to obtain the kinetic energy risk field strength of the surrounding vehicle A according to the calculation formula:
Figure FDA0003719188020000021
wherein E is sv_va The kinetic energy risk field strength of a surrounding vehicle A, A being a field strength coefficient greater than 0, M sv Is the risk quality, x, of the surrounding vehicle A obtained in step S11 ev As principal longitudinal coordinate, x sv Is the longitudinal coordinate of the surrounding vehicle A, alpha is a weight coefficient related to the speed of the surrounding vehicle A, v sv Speed of the surrounding vehicle A, w x Weight coefficient, L, for the length of the surrounding vehicle A sv Is the length of the surrounding vehicle A, y ev As longitudinal coordinate of the host car, y sv Is the lateral coordinate of the surrounding vehicle A, w y Weight coefficient, W, for the width of the surrounding vehicle A sv The width of a surrounding vehicle A is shown, theta is an included angle between the speed direction of the surrounding vehicle A and d, and the clockwise direction is positive; gamma is a weight coefficient related to the included angle theta; beta is a weight coefficient related to the acceleration of the surrounding vehicle A, a sv D is the acceleration of a certain surrounding vehicle A, d is the distance vector between the host vehicle and the surrounding vehicle A, and d is (x) ev -x sv ,y ev -y sv )。
6. The intelligent networked automobile risk assessment method according to claim 3 or 4, wherein the calculation formula of the step S14 is as follows:
Figure FDA0003719188020000022
wherein r is ev Driving risk to the host vehicle for the surrounding vehicle A, E sv The risk field intensity, m, of the surrounding vehicle A obtained in step S13 ev Is the physical mass of the master vehicle; w is a v Is the relative velocity | v of the host vehicle and the surrounding vehicle A ev -v sv A weight coefficient of | is; v. of ev Is the host vehicle speed; v. of sv A certain surrounding vehicle speed; w is a a A weight coefficient that is a principal acceleration; a is ev Is the main vehicle acceleration.
7. The intelligent networked automobile risk assessment method according to claim 2, wherein the following risk suffered by the main automobile is calculated according to the driving risk generated by the front surrounding vehicles, the left front surrounding vehicles and the right front surrounding vehicles on the main automobile in a weighted mode;
and calculating the lane change risk of the main vehicle according to the driving risk generated by the left front surrounding vehicle, the left rear surrounding vehicle, the right front surrounding vehicle and the right rear surrounding vehicle on the main vehicle.
8. An intelligent networked automobile personalized decision-making method based on the intelligent networked automobile risk assessment method of any one of claims 1 to 7, comprising the following steps: and selecting a driving style, and comparing the driving risk borne by the main vehicle with a driving risk threshold value corresponding to the driving style respectively so as to determine the driving state of the main vehicle.
9. The intelligent networked automobile personalized decision making method according to claim 8, characterized in that: the driving risks comprise a following risk and a lane changing risk, and the driving risk threshold comprises a following risk threshold and a lane changing risk threshold;
comparing the driving risk borne by the main vehicle with a driving risk threshold corresponding to the driving style so as to determine the driving state of the main vehicle in a mode of:
when the following risk of the host vehicle is smaller than or equal to the following risk threshold value, the host vehicle normally runs;
when the following risk of the main vehicle is greater than the following risk threshold value, the left and right lane changing risks of the main vehicle are respectively compared with the lane changing risk threshold value corresponding to the driving style, and the following four conditions are adopted:
if the left lane changing risk and the right lane changing risk are both smaller than or equal to the lane changing risk threshold, the main vehicle performs left lane changing or right lane changing;
if the left lane change risk is less than or equal to the lane change risk threshold and the right lane change risk is greater than the lane change risk threshold, the primary vehicle performs left lane change;
if the lane change risk on the left side is greater than the lane change risk threshold value and the lane change risk on the right side is less than or equal to the lane change risk threshold value, the main vehicle performs the lane change on the right side;
and if the left lane changing risk and the right lane changing risk are both greater than or equal to the lane changing risk threshold, the main vehicle executes braking.
10. The intelligent networked automobile personalized decision method according to claim 8 or 9, wherein the following risk threshold and lane change risk threshold are determined in a manner that: based on the public natural driving data set, the following risk and the lane changing risk of a driver under the real road driving condition are clustered and analyzed, the driving risk and the lane changing risk are divided into three classes, and the clustering centers of the three classes are respectively and correspondingly used as the following risk threshold and the lane changing risk threshold of aggressive, normal and conservative driving styles.
CN202210754129.6A 2022-06-28 2022-06-28 Intelligent networking automobile risk assessment method and personalized decision-making method Pending CN115009274A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210754129.6A CN115009274A (en) 2022-06-28 2022-06-28 Intelligent networking automobile risk assessment method and personalized decision-making method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210754129.6A CN115009274A (en) 2022-06-28 2022-06-28 Intelligent networking automobile risk assessment method and personalized decision-making method

Publications (1)

Publication Number Publication Date
CN115009274A true CN115009274A (en) 2022-09-06

Family

ID=83079693

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210754129.6A Pending CN115009274A (en) 2022-06-28 2022-06-28 Intelligent networking automobile risk assessment method and personalized decision-making method

Country Status (1)

Country Link
CN (1) CN115009274A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116363905A (en) * 2023-05-19 2023-06-30 吉林大学 Heterogeneous traffic flow converging region lane change time judging and active safety control method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116363905A (en) * 2023-05-19 2023-06-30 吉林大学 Heterogeneous traffic flow converging region lane change time judging and active safety control method
CN116363905B (en) * 2023-05-19 2023-09-05 吉林大学 Heterogeneous traffic flow converging region lane change time judging and active safety control method

Similar Documents

Publication Publication Date Title
CN110491154B (en) Suggested vehicle speed making method based on safety risk and distance
CN110085056B (en) Method for identifying instantaneous risk of vehicle lane change in expressway vehicle-road cooperative environment
CN112201038A (en) Road network risk assessment method based on risk of bad driving behavior of single vehicle
CN111547064B (en) Driving style recognition and classification method for automobile adaptive cruise system
CN112116100B (en) Game theory decision method considering driver type
CN112721949B (en) Method for evaluating longitudinal driving personification degree of automatic driving vehicle
CN103366551A (en) Road traffic safety evaluation method
CN105034986A (en) On-line identification method and on-line identification device for steering characteristics of drivers
CN110288826B (en) Traffic control subregion clustering division method based on multi-source data fusion and MILP
CN109887279B (en) Traffic jam prediction method and system
CN115009274A (en) Intelligent networking automobile risk assessment method and personalized decision-making method
CN115620530A (en) Automatic driving takeover risk assessment model considering driving risk field and construction method thereof
CN112201070B (en) Deep learning-based automatic driving expressway bottleneck section behavior decision method
CN114169444A (en) Driving style classification method considering risk potential field distribution under vehicle following working condition
CN109455178A (en) A kind of road vehicles traveling active control system and method based on binocular vision
CN113487197A (en) TOPSIS (technique for order preference by similarity to Ideal solution) evaluation model-based vehicle networking information screening method
CN114492043B (en) Personalized driver following modeling method considering perception limited characteristics
CN113592221B (en) Road section risk dynamic assessment method based on safety substitution evaluation index
EP4403432A1 (en) Autonomous driving method and system capable of recognizing road conditions, and vehicle
CN115171389B (en) Highway other vehicle overtaking lane changing intention recognition method based on GMM-HMM
CN109910865A (en) A kind of vehicle early warning brake method based on Internet of Things
CN112036709B (en) Random forest based rainfall weather expressway secondary accident cause analysis method
CN112319479B (en) Vehicle longitudinal driving safety distance estimation method based on vehicle trust
CN114889589A (en) Intelligent automobile steering and braking cooperative collision avoidance control system and method
CN106250637B (en) Automobile safety system parameter optimization method based on micro- Traffic Flow Simulation Models

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