CN111994079A - Non-cooperative game lane change auxiliary decision making system and method considering driving style characteristics - Google Patents

Non-cooperative game lane change auxiliary decision making system and method considering driving style characteristics Download PDF

Info

Publication number
CN111994079A
CN111994079A CN202010987287.7A CN202010987287A CN111994079A CN 111994079 A CN111994079 A CN 111994079A CN 202010987287 A CN202010987287 A CN 202010987287A CN 111994079 A CN111994079 A CN 111994079A
Authority
CN
China
Prior art keywords
lane change
lane
vehicle
driver
decision
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
CN202010987287.7A
Other languages
Chinese (zh)
Inventor
罗建
赵万忠
栾众楷
郑双权
董雪锋
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.)
Nanjing University of Aeronautics and Astronautics
Original Assignee
Nanjing University of Aeronautics and Astronautics
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 Nanjing University of Aeronautics and Astronautics filed Critical Nanjing University of Aeronautics and Astronautics
Priority to CN202010987287.7A priority Critical patent/CN111994079A/en
Publication of CN111994079A publication Critical patent/CN111994079A/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, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/18—Propelling the vehicle
    • B60W30/18009—Propelling the vehicle related to particular drive situations
    • B60W30/18163—Lane change; Overtaking manoeuvres
    • 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
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B60W40/04—Traffic conditions
    • 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
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B60W40/09—Driving style or behaviour
    • 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
    • B60W2540/00—Input parameters relating to occupants
    • B60W2540/30—Driving style
    • 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
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/50—Barriers
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/20—Static objects
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects

Abstract

The invention discloses a non-cooperative game lane change auxiliary decision-making system and method considering driving style characteristics, which comprises the following steps: the driving environment data acquisition module is used for acquiring position data and motion data of surrounding mobile units and static units of the networked vehicles to obtain a driving environment data set; the lane change motivation judging module is used for receiving the driving environment data set, analyzing and calculating the driving environment data set and judging whether a driver has a lane change motivation or not; the lane change income calculating and judging module is used for receiving the lane change motivation instruction, performing game income calculation and driving style calculation, obtaining a lane change income result and judging income level; and the lane changing auxiliary decision prompting module prompts the driver to execute lane changing or give up lane changing according to the income height information. The method deeply analyzes the influence of the game lane changing scene and the driving style and combines the scene and the driving style, so that the lane changing decision making efficiency of the proposed model decision making method is higher than that of a single lane changing decision making method based on a game model.

Description

Non-cooperative game lane change auxiliary decision making system and method considering driving style characteristics
Technical Field
The invention relates to the technical field of vehicle safety, in particular to a non-cooperative game lane change auxiliary decision-making system and method considering driving style characteristics.
Background
The driver takes different driving behaviors according to the change of the road environment and the surrounding vehicle information during the driving process of the vehicle. In the two driving behaviors of lane changing and following, due to the complexity of the lane changing process, traffic accidents are more easily caused by the misjudgment of lane changing. Under the internet environment, the driving assistance system can provide effective decision assistance for the lane changing behavior of the driver through comprehensive perception of the surrounding environment and the vehicle.
Most of lane change decision models adopted by the conventional lane change driving auxiliary system are established based on vehicle kinematics rules, lane change dangers can be pre-warned only before a vehicle lane change, the process of realizing an inductive decision due to influence of factors of a driver cannot be accurately reflected, and the driving behavior change of the driver in the lane change process is difficult to reflect.
Disclosure of Invention
In view of the above disadvantages of the prior art, the present invention provides a non-cooperative game lane change assistant decision system and method considering driving style characteristics, so as to solve the problem that the lane change driving assistant system in the prior art cannot accurately reflect the process of implementing perceptual decision due to the influence of the driver's factors, and is difficult to reflect the change of the driving behavior of the driver in the lane change process. The lane changing auxiliary decision-making method is more flexible and applicable by combining the thought of the non-cooperative game theory and the characteristics of the driver.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the invention discloses a non-cooperative game lane change auxiliary decision-making system considering driving style characteristics, which comprises:
the driving environment data acquisition module is used for acquiring position data and motion data of surrounding mobile units and static units of the networked vehicles to obtain a driving environment data set;
the lane change motivation judging module is used for receiving the driving environment data set, analyzing and calculating the driving environment data set, judging whether a driver has a lane change motivation or not, and generating a lane change motivation instruction if the driver has the lane change motivation;
the lane change income calculating and judging module is used for receiving the lane change motivation instruction, performing game income calculation and driving style calculation, obtaining a lane change income result and judging income level;
and the lane change auxiliary decision prompting module prompts the driver to execute lane change or give up lane change according to the income height information.
Further, the method for judging whether the lane change motivation exists by the lane change motivation judging module is as follows:
Figure BDA0002689675010000011
Figure BDA0002689675010000012
wherein, Δ xiRepresenting a distance between the target vehicle and the obstacle; t issafeIndicating a safe time interval, TminRepresents the minimum reaction time;
Figure BDA0002689675010000021
vi+1representing a desired speed, an actual speed of the target vehicle, and an actual speed of the lead vehicle, respectively; v. ofbarTo influence the speed of movement of the object on which the target vehicle continues to travel.
Further, the method for calculating the lane change profit by the lane change profit calculating and judging module is as follows:
the revenue function calculation formula is as follows:
g or G ═ alpha1*+α2*
Wherein, the values of the safety gain and the aging gain obtained by the current vehicle when the lane change decision is carried out are calculated by the following formula:
Figure BDA0002689675010000022
Figure BDA0002689675010000023
in the formula, SminA minimum safe distance required for making a lane change decision; t is the time required to reach the target site, t0In order to keep the time required for reaching the destination in the original state, S is the distance to the destination, and the calculation of the revenue function is converted into the minimum safety distance required for solving the lane change decision and the time required for reaching the destination;
wherein alpha is1、α2As a weight coefficient, drivers with different styles have different requirements on efficiency and safety, the weights are different, the initial values are arbitrary, and the alpha is satisfied1，α2∈{α1+α2＝1，0<α1、α2＜1}，α1、α2The value rule is as follows:
Figure BDA0002689675010000024
α2＝1-α1
in the formula, RdriverFor the driver style recognition coefficient, the calculation formula is as follows:
Figure BDA0002689675010000025
in the formula, RJ，
Figure BDA0002689675010000026
Respectively identifying the standard deviation of the impact degree J (t) in the domain and the average value of a standard driver under the current working condition; the degree of impact j (t) is measured as the vehicle speed v (t) and is defined as:
Figure BDA0002689675010000027
in the formula, the average value of J (t) is 0.59, 0.31, 0.26 and 0.25 respectively in the crowded working condition, the urban working condition, the suburban working condition and the highway working condition.
The invention discloses a non-cooperative game lane change auxiliary decision-making method considering driving style characteristics, which comprises the following steps of:
step 1) judging whether a driver has a lane change motivation or not according to collected driving environment data; if no lane change motivation exists, entering the step 4), and if the lane change motivation exists, entering the step 2);
step 2), carrying out game lane change decision and constructing a game income matrix;
step 3) solving all Nash balanced mixed strategy combinations according to the gain matrix obtained in the step 2), and judging the gain level; if the income is low, prompting the driver to give up the lane change, and entering the step 4); if the income is high, prompting the driver to recommend lane changing, and entering the step 5);
step 4) advising to abandon the lane change, and entering step 6);
step 5) advising to execute lane changing and entering step 6);
and 6) finishing the decision.
Further, the method for determining whether the driver has a lane change motivation in step 1) is as follows:
Figure BDA0002689675010000031
Figure BDA0002689675010000032
in the formula,. DELTA.xiRepresenting a distance between the target vehicle and the obstacle; t issafeIndicating a safe time interval, TminRepresents the minimum reaction time;
Figure BDA0002689675010000033
vi+1representing a desired speed, an actual speed of the target vehicle, and an actual speed of the lead vehicle, respectively; v. ofbarTo influence the speed of movement of the object on which the target vehicle continues to travel.
Further, the step 2) specifically includes: under the complete information static non-cooperative game, the strategy set for defining the target vehicle M is phi1The strategy comprises the following steps of { C, N }, wherein C represents lane change, N is lane change failure, and the corresponding probability of the strategy is p and 1-p respectively; following vehicle B of adjacent lane1Has a policy set of phi2The strategy comprises the following steps of { D, R }, wherein D is allowed lane changing, R is refused lane changing, and the strategy corresponding probability is q and 1-q; m and B1G for profitij、gijRepresenting to obtain a game income matrix;
Figure BDA0002689675010000041
target vehicle M changes lane, following vehicle B after adjacent lane1Allow lane change, at which time M and B1The earnings are respectively G11And g11(ii) a Target vehicle M does not change lane, and following vehicle B follows adjacent lane1Allow lane change, at which time M and B1The earnings are respectively G12And g12(ii) a Target vehicle M changes lane, following vehicle B after adjacent lane1The lane change is not allowed, at this time M and B1The earnings are respectively G21And g21(ii) a Target vehicle M does not change lane, and following vehicle B follows adjacent lane1The lane change is not allowed, at this time M and B1The earnings are respectively G22And g22。
Further, the step 3) specifically includes: and (3) calculating each revenue function of the mixing strategy, wherein the revenue function calculation formula is as follows:
G＝α1*+α2* (1)
wherein, the safety benefit and the aging benefit obtained for the current vehicle for making the lane change decision are respectively obtained; alpha is alpha1、α2The weighting coefficient is the weight coefficient, the weights of drivers with different styles have different requirements on efficiency and safety, the initial values are arbitrary, and the alpha is satisfied1，α2∈{α1+α2＝1，0<α1、α2＜1}；
Quantizing the driving style, and generating impact degree R in the driving processdriverCharacterizing the driver style recognition coefficient, and calculating the formula as follows:
Figure BDA0002689675010000042
wherein R isJ，
Figure BDA0002689675010000043
Respectively identifying the standard deviation of the impact degree J (t) in the domain and the average value of a standard driver under the current working condition; the degree of impact j (t) is measured as the vehicle speed v (t) and is defined as:
Figure BDA0002689675010000044
wherein, the average value of J (t) is respectively 0.59, 0.31, 0.26 and 0.25 in the crowded working condition, the urban working condition, the suburban working condition and the highway working condition;
calculating the impact degree R generated in the driving process according to the vehicle speed information in the monitoring timedriverComparing the result with a constant RaggAnd Rnorm；RnormRepresenting a critical value of a common driving style, and the value is 0.5, RaggRepresenting an aggressive driving style critical value, and taking the value as 1; if R isdriver＜RnormThe driving style of the driver is cautious, if Rdriver＞RaggIf the style of the vehicle is between the two types, the style of the vehicle is of an aggressive type, and if the style of the vehicle is between the two types, the vehicle is of a normal type.
Different requirements for safety and time efficiency when the driver's driving style is different, i.e. alpha1、α2The values are different:
Figure BDA0002689675010000051
α2＝1-α1 (5)
the safety benefit and the aging benefit are calculated as follows:
Figure BDA0002689675010000052
Figure BDA0002689675010000053
in the formula, SminMinimum safety distance required for decision making; t is the time currently required to reach the target location, t0S is the distance to the destination in order to keep the time required for reaching the destination in the original state; the calculation of the revenue function is converted into the minimum safety distance required by decision making and the time taken for reaching the destination;
in the following state, the leading vehicle decides the response of the following vehicle, and the minimum safe distance model is:
Figure BDA0002689675010000054
wherein, VF(t) is the front speed, VL(t) is rear speed, beta11/w is the current vehicle-to-lead vehicle reaction time, w is the width of the vehicle, β2Is the inverse of twice the maximum deceleration of the current vehicle, and is calibrated according to parameters, wherein gamma is-beta1；
When changing lanes, the collision possibly occurring in the lane changing vehicles is an oblique collision, the minimum lane changing safe distance is modeled, and M and B are1The conditions for avoiding collision are as follows:
Figure BDA0002689675010000056
and is
Figure BDA0002689675010000055
The distance between the two vehicles in the driving direction is as follows:
Figure BDA0002689675010000057
wherein theta is an included angle between the tangential direction of the advancing track of the vehicle M and the longitudinal direction of the road;
then:
Figure BDA0002689675010000061
the formula (12) is an essential condition for non-collision lane change, wherein,
Figure BDA0002689675010000065
aMare respectively B1And the longitudinal acceleration of the M cars;
as long as h > 0 is guaranteed during the lane change, no collision occurs, from which it follows:
Figure BDA0002689675010000066
and similarly, changing the minimum safe distance:
Figure BDA0002689675010000062
and obtaining the time for reaching the destination through the distance of the destination and the initial speed of the vehicle.
Further, the step 3) specifically further includes: under the Nash equilibrium strategy combination, the decision made by any one game participant is the optimal decision for other participants; on the basis, comparing M and B with the game income matrix described in the step 2)1The probabilities of the selected decisions are denoted as vector x ═ x (x), respectively1,x2)，y＝(y1,y2)TThen, the solution of the solved mixing strategy Nash balance is:
Figure BDA0002689675010000063
is equivalent to:
Figure BDA0002689675010000064
solving (p) the yield calculations in the game yield matrix*,q*) The solution of a mixed strategy Nash balanced combination which is the non-cooperative game lane changing is satisfied.
Further, the road change income of the target vehicle is judged according to the solution in the step 3), and when the road change income is more than 1000, the safety income is high; otherwise, it is low; when the yield is more than 800, the aging yield is high, otherwise, the aging yield is low; the profit-level determination rule is as follows:
when G > 1000 x alpha1+800*α2When the target vehicle lane change income is high, otherwise, the target vehicle lane change income is low.
The invention has the beneficial effects that:
the method can assist the driver to make lane change decision in a scene closer to the reality, and introduces the style coefficient into the income calculation, so that the decision method is closer to the actual driving condition, and the influence of different styles on expected income is reflected; meanwhile, the development of a driving auxiliary system and the lane change decision of the internet vehicle are facilitated. The existing lane change decision based on the cellular automaton model only analyzes lane change vehicles, ignores the existence of the dynamic interaction influence of related vehicles, and simultaneously has harsh lane change rules, so that the lane change efficiency of target vehicles is low. The invention deeply analyzes the influence of the game lane changing scene and the driving style and combines the scene and the driving style, so that the lane changing decision making efficiency of the proposed model decision making method is higher than the lane changing decision making efficiency of a pure game model.
Drawings
FIG. 1 is a schematic block diagram of the system of the present invention.
FIG. 2 is a flow chart of the method of the present invention.
Detailed Description
In order to facilitate understanding of those skilled in the art, the present invention will be further described with reference to the following examples and drawings, which are not intended to limit the present invention.
Referring to fig. 1, the non-cooperative game lane change assistant decision-making system considering driving style characteristics of the invention comprises:
the driving environment data acquisition module is used for acquiring position data and motion data of surrounding mobile units and static units of the networked vehicles to obtain a driving environment data set;
the lane change motivation judging module is used for receiving the driving environment data set, analyzing and calculating the driving environment data set, judging whether a driver has a lane change motivation or not, and generating a lane change motivation instruction if the driver has the lane change motivation;
the lane change income calculating and judging module is used for receiving the lane change motivation instruction, performing game income calculation and driving style calculation, obtaining a lane change income result and judging income level;
and the lane change auxiliary decision prompting module prompts the driver to execute lane change or give up lane change according to the income height information.
The method for judging whether the lane changing motivation exists by the lane changing motivation judging module is as follows:
Figure BDA0002689675010000071
Figure BDA0002689675010000072
wherein, Δ xiRepresenting a distance between the target vehicle and the obstacle; t issafeIndicating a safe time interval, TminRepresents the minimum reaction time;
Figure BDA0002689675010000073
vi+1are respectively provided withRepresenting a desired speed of the target vehicle, an actual speed, and an actual speed of the lead vehicle; v. ofbarTo influence the speed of movement of the object on which the target vehicle continues to travel.
The method for calculating the lane change income by the lane change income calculating and judging module comprises the following steps:
the revenue function calculation formula is as follows:
g or G ═ alpha1*+α2*
Wherein, the values of the safety gain and the aging gain obtained by the current vehicle when the lane change decision is carried out are calculated by the following formula:
Figure BDA0002689675010000074
Figure BDA0002689675010000081
in the formula, SminA minimum safe distance required for making a lane change decision; t is the time required to reach the target site, t0In order to keep the time required for reaching the destination in the original state, S is the distance to the destination, and the calculation of the revenue function is converted into the minimum safety distance required for solving the lane change decision and the time required for reaching the destination;
wherein alpha is1、α2As a weight coefficient, drivers with different styles have different requirements on efficiency and safety, the weights are different, the initial values are arbitrary, and the alpha is satisfied1，α2∈{α1+α2＝1，0<α1、α2＜1}，α1、α2The value rule is as follows:
Figure BDA0002689675010000082
α2＝1-α1
in the formula, RdriverCalculating a driver style recognition coefficientThe formula is as follows:
Figure BDA0002689675010000083
in the formula, RJ，
Figure BDA0002689675010000084
Respectively identifying the standard deviation of the impact degree J (t) in the domain and the average value of a standard driver under the current working condition; the degree of impact j (t) is measured as the vehicle speed v (t) and is defined as:
Figure BDA0002689675010000085
in the formula, the average value of J (t) is 0.59, 0.31, 0.26 and 0.25 respectively in the crowded working condition, the urban working condition, the suburban working condition and the highway working condition.
Referring to fig. 2, the non-cooperative game lane change assistant decision method considering driving style characteristics of the invention comprises the following steps:
step 1) judging whether a driver has a lane change motivation or not according to collected driving environment data; if no lane change motivation exists, entering the step 4), and if the lane change motivation exists, entering the step 2);
the method for judging whether the driver has the lane change motivation is as follows:
Figure BDA0002689675010000091
Figure BDA0002689675010000092
in the formula,. DELTA.xiRepresenting a distance between the target vehicle and the obstacle; t issafeIndicating a safe time interval, TminRepresents the minimum reaction time;
Figure BDA0002689675010000093
vi+1representing a desired speed, an actual speed of the target vehicle, and an actual speed of the lead vehicle, respectively; v. ofbarTo influence the speed of movement of the object on which the target vehicle continues to travel.
Step 2), carrying out game lane change decision and constructing a game income matrix;
under the complete information static non-cooperative game, the strategy set for defining the target vehicle M is phi1The strategy comprises the following steps of { C, N }, wherein C represents lane change, N is lane change failure, and the corresponding probability of the strategy is p and 1-p respectively; following vehicle B of adjacent lane1Has a policy set of phi2The strategy comprises the following steps of { D, R }, wherein D is allowed lane changing, R is refused lane changing, and the strategy corresponding probability is q and 1-q; m and B1G for profitij、gijRepresenting to obtain a game income matrix;
Figure BDA0002689675010000094
target vehicle M changes lane, following vehicle B after adjacent lane1Allow lane change, at which time M and B1The earnings are respectively G11And g11(ii) a Target vehicle M does not change lane, and following vehicle B follows adjacent lane1Allow lane change, at which time M and B1The earnings are respectively G12And g12(ii) a Target vehicle M changes lane, following vehicle B after adjacent lane1The lane change is not allowed, at this time M and B1The earnings are respectively G21And g21(ii) a Target vehicle M does not change lane, and following vehicle B follows adjacent lane1The lane change is not allowed, at this time M and B1The earnings are respectively G22And g22。
Step 3) solving all Nash balanced mixed strategy combinations according to the gain matrix obtained in the step 2), and judging the gain level; if the income is low, prompting the driver to give up the lane change, and entering the step 4); if the income is high, prompting the driver to recommend lane changing, and entering the step 5);
and (3) calculating each revenue function of the mixing strategy, wherein the revenue function calculation formula is as follows:
G＝α1*+α2* (1)
wherein, the safety benefit and the aging benefit obtained for the current vehicle for making the lane change decision are respectively obtained; alpha is alpha1、α2The weighting coefficient is the weight coefficient, the weights of drivers with different styles have different requirements on efficiency and safety, the initial values are arbitrary, and the alpha is satisfied1，α2∈{α1+α2＝1，0<α1、α2＜1}；
Quantizing the driving style, and generating impact degree R in the driving processdriverCharacterizing the driver style recognition coefficient, and calculating the formula as follows:
Figure BDA0002689675010000101
wherein R isJ，
Figure BDA0002689675010000102
Respectively identifying the standard deviation of the impact degree J (t) in the domain and the average value of a standard driver under the current working condition; the degree of impact j (t) is measured as the vehicle speed v (t) and is defined as:
Figure BDA0002689675010000103
wherein, the average value of J (t) is respectively 0.59, 0.31, 0.26 and 0.25 in the crowded working condition, the urban working condition, the suburban working condition and the highway working condition;
calculating the impact degree R generated in the driving process according to the vehicle speed information in the monitoring timedriverComparing the result with a constant RaggAnd Rnorm；RnormRepresenting a critical value of a common driving style, and the value is 0.5, RaggRepresenting an aggressive driving style critical value, and taking the value as 1; if R isdriver＜RnormThe driving style of the driver is cautious, if Rdriver＞RaggIf the style of the vehicle is between the two types, the style of the vehicle is of an aggressive type, and if the style of the vehicle is between the two types, the vehicle is of a normal type.
Different requirements for safety and time efficiency when the driver's driving style is different, i.e. alpha1、α2The values are different:
Figure BDA0002689675010000104
α2＝1-α1 (5)
the safety benefit and the aging benefit are calculated as follows:
Figure BDA0002689675010000105
Figure BDA0002689675010000106
in the formula, SminMinimum safety distance required for decision making; t is the time currently required to reach the target location, t0S is the distance to the destination in order to keep the time required for reaching the destination in the original state; the calculation of the revenue function is converted into the minimum safety distance required by decision making and the time taken for reaching the destination;
in the following state, the leading vehicle decides the response of the following vehicle, and the minimum safe distance model is:
Figure BDA0002689675010000111
wherein, VF(t) is the front speed, VL(t) is rear speed, beta11/w is the current vehicle-to-lead vehicle reaction time, w is the width of the vehicle, β2Is the inverse of twice the maximum deceleration of the current vehicle, and is calibrated according to parameters, wherein gamma is-beta1；
When changing lanes, the collision possibly occurring in the lane changing vehicles is an oblique collision, the minimum lane changing safe distance is modeled, and M and B are1The conditions for avoiding collision are as follows:
Figure BDA0002689675010000115
and is
Figure BDA0002689675010000112
The distance between the two vehicles in the driving direction is as follows:
Figure BDA0002689675010000116
wherein theta is an included angle between the tangential direction of the advancing track of the vehicle M and the longitudinal direction of the road;
then:
Figure BDA0002689675010000113
the formula (12) is an essential condition for non-collision lane change, wherein,
Figure BDA0002689675010000117
aMare respectively B1And the longitudinal acceleration of the M cars;
as long as h > 0 is guaranteed during the lane change, no collision occurs, from which it follows:
Figure BDA0002689675010000118
and similarly, changing the minimum safe distance:
Figure BDA0002689675010000114
and obtaining the time for reaching the destination through the distance of the destination and the initial speed of the vehicle.
The step 3) specifically further comprises: under the combination of the Nash balancing strategy,the decision made by any one of the gaming participants is an optimal decision for the other participants; on the basis, comparing M and B with the game income matrix described in the step 2)1The probabilities of the selected decisions are denoted as vector x ═ x (x), respectively1,x2)，y＝(y1,y2)TThen, the solution of the solved mixing strategy Nash balance is:
Figure BDA0002689675010000121
is equivalent to:
Figure BDA0002689675010000122
solving (p) the yield calculations in the game yield matrix*,q*) The solution of a mixed strategy Nash balanced combination which is the non-cooperative game lane changing is satisfied.
Judging the profit of the lane change of the target vehicle according to the solution obtained in the step 3), and when the profit is more than 1000, the safety profit is high; otherwise, it is low; when the yield is more than 800, the aging yield is high, otherwise, the aging yield is low; the profit-level determination rule is as follows:
when G > 1000 x alpha1+800*α2When the target vehicle lane change income is high, otherwise, the target vehicle lane change income is low.
Step 4) advising to abandon the lane change, and entering step 6);
step 5) advising to execute lane changing and entering step 6);
and 6) finishing the decision.
While the invention has been described in terms of its preferred embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.

Claims (9)

1. A non-cooperative game lane change aid decision-making system considering driving style characteristics is characterized by comprising:
the driving environment data acquisition module is used for acquiring position data and motion data of surrounding mobile units and static units of the networked vehicles to obtain a driving environment data set;
the lane change motivation judging module is used for receiving the driving environment data set, analyzing and calculating the driving environment data set, judging whether a driver has a lane change motivation or not, and generating a lane change motivation instruction if the driver has the lane change motivation;
the lane change income calculating and judging module is used for receiving the lane change motivation instruction, performing game income calculation and driving style calculation, obtaining a lane change income result and judging income level;
and the lane change auxiliary decision prompting module prompts the driver to execute lane change or give up lane change according to the income height information.
2. The non-cooperative game lane change aid decision system taking the driving style characteristics into consideration as claimed in claim 1, wherein the lane change motivation judging module judges whether the lane change motivation exists according to the following method:
Figure FDA0002689673000000011
Figure FDA0002689673000000012
wherein, Δ xiRepresenting a distance between the target vehicle and the obstacle; t issafeIndicating a safe time interval, TminRepresents the minimum reaction time;
Figure FDA0002689673000000013
vi+1representing a desired speed, an actual speed of the target vehicle, and an actual speed of the lead vehicle, respectively; v. ofbarTo influence the speed of movement of the object on which the target vehicle continues to travel.
3. The non-cooperative game lane change aid decision making system considering driving style characteristics as claimed in claim 1, wherein the lane change benefit calculation and judgment module calculates the following method:
the revenue function calculation formula is as follows:
g or G ═ alpha1*+α2*
Wherein, the values of the safety gain and the aging gain obtained by the current vehicle when the lane change decision is carried out are calculated by the following formula:
Figure FDA0002689673000000014
Figure FDA0002689673000000015
in the formula, SminA minimum safe distance required for making a lane change decision; t is the time required to reach the target site, t0In order to keep the time required for reaching the destination in the original state, S is the distance to the destination, and the calculation of the revenue function is converted into the minimum safety distance required for solving the lane change decision and the time required for reaching the destination;
wherein alpha is1、α2As a weight coefficient, drivers with different styles have different requirements on efficiency and safety, the weights are different, the initial values are arbitrary, and the alpha is satisfied1，α2∈{α1+α2＝1，0<α1、α2＜1}，α1、α2The value rule is as follows:
Figure FDA0002689673000000021
α2＝1-α1
in the formula, RdriverFor the driver style recognition coefficient, the calculation formula is as follows:
Figure FDA0002689673000000022
in the formula, RJ，
Figure FDA0002689673000000023
Respectively identifying the standard deviation of the impact degree J (t) in the domain and the average value of a standard driver under the current working condition; the degree of impact j (t) is measured as the vehicle speed v (t) and is defined as:
Figure FDA0002689673000000024
in the formula, the average value of J (t) is 0.59, 0.31, 0.26 and 0.25 respectively in the crowded working condition, the urban working condition, the suburban working condition and the highway working condition.
4. A non-cooperative game lane change auxiliary decision method considering driving style characteristics is characterized by comprising the following steps:
step 1) judging whether a driver has a lane change motivation or not according to collected driving environment data; if no lane change motivation exists, entering the step 4), and if the lane change motivation exists, entering the step 2);
step 2), carrying out game lane change decision and constructing a game income matrix;
step 3) solving all Nash balanced mixed strategy combinations according to the gain matrix obtained in the step 2), and judging the gain level; if the income is low, prompting the driver to give up the lane change, and entering the step 4); if the income is high, prompting the driver to recommend lane changing, and entering the step 5);
step 4) advising to abandon the lane change, and entering step 6);
step 5) advising to execute lane changing and entering step 6);
and 6) finishing the decision.
5. The non-cooperative game lane change assistant decision method taking the driving style characteristics into consideration as claimed in claim 1, wherein the method for judging whether the driver has the lane change motivation in the step 1) is as follows:
Figure FDA0002689673000000031
Figure FDA0002689673000000032
in the formula,. DELTA.xiRepresenting a distance between the target vehicle and the obstacle; t issafeIndicating a safe time interval, TminRepresents the minimum reaction time;
Figure FDA0002689673000000033
vi+1representing a desired speed, an actual speed of the target vehicle, and an actual speed of the lead vehicle, respectively; v. ofbarTo influence the speed of movement of the object on which the target vehicle continues to travel.
6. The non-cooperative game lane change assistant decision method considering driving style characteristics as claimed in claim 1, wherein the step 2) specifically comprises: under the complete information static non-cooperative game, the strategy set for defining the target vehicle M is phi1The strategy comprises the following steps that 1, the strategy is divided into two strategies, wherein the strategy comprises the following steps of { C, N }, C denotes lane changing, N is not lane changing, and the corresponding probability of the strategy is p and 1-p respectively; following vehicle B of adjacent lane1Has a policy set of phi2D is allowed to switch channels, R is refused to switch channels, and the corresponding probability of the strategy is q and 1-q; m and B1G for profitij、gijRepresenting to obtain a game income matrix;
Figure FDA0002689673000000034
target vehicle M changes lane, following vehicle B after adjacent lane1Allowing for changingWay, at this time M and B1The earnings are respectively G11And g11(ii) a Target vehicle M does not change lane, and following vehicle B follows adjacent lane1Allow lane change, at which time M and B1The earnings are respectively G12And g12(ii) a Target vehicle M changes lane, following vehicle B after adjacent lane1The lane change is not allowed, at this time M and B1The earnings are respectively G21And g21(ii) a Target vehicle M does not change lane, and following vehicle B follows adjacent lane1The lane change is not allowed, at this time M and B1The earnings are respectively G22And g22。
7. The non-cooperative game lane change assistant decision method considering driving style characteristics as claimed in claim 1, wherein the step 3) specifically comprises: and (3) calculating each revenue function of the mixing strategy, wherein the revenue function calculation formula is as follows:
G＝α1*+α2* (1)
in the formula, the safety benefit and the aging benefit obtained for the current vehicle for making the lane change decision are respectively obtained; alpha is alpha1、α2The weighting coefficient is the weight coefficient, the weights of drivers with different styles have different requirements on efficiency and safety, the initial values are arbitrary, and the alpha is satisfied1，α2∈{α1+α2＝1，0<α1、α2＜1}；
Quantizing the driving style, and generating impact degree R in the driving processdriverCharacterizing the driver style recognition coefficient, and calculating the formula as follows:
Figure FDA0002689673000000041
in the formula, RJ，
Figure FDA0002689673000000042
Respectively identifying the standard deviation of the impact degree J (t) in the domain and the average value of a standard driver under the current working condition; the degree of impact j (t) is measured as the vehicle speed v (t) and is defined as:
Figure FDA0002689673000000043
in the formula, the average value of J (t) is respectively 0.59, 0.31, 0.26 and 0.25 in the crowded working condition, the urban working condition, the suburban working condition and the highway working condition;
calculating the impact degree R generated in the driving process according to the vehicle speed information in the monitoring timedriverComparing the result with a constant RaggAnd Rnorm；RnormRepresenting a critical value of a common driving style, and the value is 0.5, RaggRepresenting an aggressive driving style critical value, and taking the value as 1; if R isdriver＜RnormThe driving style of the driver is cautious, if Rdriver＞RaggIf the style of the driver is in the aggressive style, the driver is in the normal style if the style is between the aggressive style and the normal style;
different requirements for safety and time efficiency when the driver's driving style is different, i.e. alpha1、α2The values are different:
Figure FDA0002689673000000044
α2＝1-α1 (5)
the safety benefit and the aging benefit are calculated as follows:
Figure FDA0002689673000000045
Figure FDA0002689673000000046
in the formula, SminMinimum safety distance required for decision making; t is the time currently required to reach the target location, t0To remain in the original stateThe time required for reaching the destination is given, and S is the distance from the destination to the destination; the calculation of the revenue function is converted into the minimum safety distance required by decision making and the time taken for reaching the destination;
in the following state, the leading vehicle decides the response of the following vehicle, and the minimum safe distance model is:
Figure FDA0002689673000000047
in the formula, VF(t) is the front speed, VL(t) is rear speed, beta11/w is the current vehicle-to-lead vehicle reaction time, w is the width of the vehicle, β2Is the inverse of twice the maximum deceleration of the current vehicle, and is calibrated according to parameters, wherein gamma is-beta1；
When changing lanes, the collision possibly occurring in the lane changing vehicles is an oblique collision, the minimum lane changing safe distance is modeled, and M and B are1The conditions for avoiding collision are as follows:
Figure FDA0002689673000000051
and is
Figure FDA0002689673000000052
The distance between the two vehicles in the driving direction is as follows:
Figure FDA0002689673000000053
wherein theta is an included angle between the tangential direction of the advancing track of the vehicle M and the longitudinal direction of the road;
then:
Figure FDA0002689673000000054
the formula (12) is an essential condition for non-collision lane change, wherein,
Figure FDA0002689673000000055
aMare respectively B1And the longitudinal acceleration of the M cars;
as long as h > 0 is guaranteed during the lane change, no collision occurs, from which it follows:
Figure FDA0002689673000000056
and similarly, changing the minimum safe distance:
Figure FDA0002689673000000057
and obtaining the time for reaching the destination through the distance of the destination and the initial speed of the vehicle.
8. The non-cooperative game lane change assistant decision method taking driving style characteristics into consideration of claim 7, wherein the step 3) specifically comprises the following steps: under the Nash equilibrium strategy combination, the decision made by any one game participant is the optimal decision for other participants; on the basis, comparing M and B with the game income matrix described in the step 2)1The probabilities of the selected decisions are denoted as vector x ═ x (x), respectively1,x2)，y＝(y1,y2)TThen, the solution of the solved mixing strategy Nash balance is:
Figure FDA0002689673000000061
is equivalent to:
Figure FDA0002689673000000062
solving (p) the yield calculations in the game yield matrix*,q*) The solution of a mixed strategy Nash balanced combination which is the non-cooperative game lane changing is satisfied.
9. The non-cooperative game lane change auxiliary decision-making method considering the driving style characteristics as claimed in claim 1, wherein the profit of lane change of the target vehicle is judged according to the solution of step 3), and when the profit is more than 1000, the safety profit is high; otherwise, it is low; when the yield is more than 800, the aging yield is high, otherwise, the aging yield is low; the profit-level determination rule is as follows:
when G > 1000 x alpha1+800*α2When the target vehicle lane change income is high, otherwise, the target vehicle lane change income is low.
CN202010987287.7A 2020-09-18 2020-09-18 Non-cooperative game lane change auxiliary decision making system and method considering driving style characteristics Pending CN111994079A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010987287.7A CN111994079A (en) 2020-09-18 2020-09-18 Non-cooperative game lane change auxiliary decision making system and method considering driving style characteristics

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010987287.7A CN111994079A (en) 2020-09-18 2020-09-18 Non-cooperative game lane change auxiliary decision making system and method considering driving style characteristics

Publications (1)

Publication Number Publication Date
CN111994079A true CN111994079A (en) 2020-11-27

Family

ID=73475634

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010987287.7A Pending CN111994079A (en) 2020-09-18 2020-09-18 Non-cooperative game lane change auxiliary decision making system and method considering driving style characteristics

Country Status (1)

Country Link
CN (1) CN111994079A (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112907967A (en) * 2021-01-29 2021-06-04 吉林大学 Intelligent vehicle lane change decision-making method based on incomplete information game
CN113096379A (en) * 2021-03-03 2021-07-09 东南大学 Driving style identification method based on traffic conflict
CN113200056A (en) * 2021-06-22 2021-08-03 吉林大学 Incomplete information non-cooperative game man-machine co-driving control method
CN113282413A (en) * 2021-05-20 2021-08-20 南京航空航天大学 QoS demand self-adaptive resource allocation method in vehicle edge computing network
CN113516846A (en) * 2021-06-24 2021-10-19 长安大学 Vehicle lane change behavior prediction model construction, prediction and early warning method and system
CN113942504A (en) * 2020-07-16 2022-01-18 华为技术有限公司 Self-adaptive cruise control method and device
WO2022134711A1 (en) * 2020-12-24 2022-06-30 华为技术有限公司 Driving style recognition method, assisted driving method, and apparatuses
CN114882705A (en) * 2022-05-30 2022-08-09 武汉理工大学 Freight vehicle interactive game lane change decision-making method based on lane change decision-making system
CN114919578A (en) * 2022-07-20 2022-08-19 北京理工大学前沿技术研究院 Intelligent vehicle behavior decision method, planning method, system and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107161155A (en) * 2017-04-27 2017-09-15 大连理工大学 A kind of vehicle collaboration lane-change method and its system based on artificial neural network
CN108595823A (en) * 2018-04-20 2018-09-28 大连理工大学 A kind of computational methods of Autonomous Vehicles lane-change strategy that combining driving style and theory of games
CN110362910A (en) * 2019-07-05 2019-10-22 西南交通大学 Automatic driving vehicle lane-change conflict coordination method for establishing model based on game theory
CN110962853A (en) * 2019-11-25 2020-04-07 浙江工业大学 Vehicle game lane change cooperation method in Internet of vehicles environment
CN111311947A (en) * 2020-03-02 2020-06-19 清华大学 Driving risk assessment method and device considering driver intention in internet environment

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107161155A (en) * 2017-04-27 2017-09-15 大连理工大学 A kind of vehicle collaboration lane-change method and its system based on artificial neural network
CN108595823A (en) * 2018-04-20 2018-09-28 大连理工大学 A kind of computational methods of Autonomous Vehicles lane-change strategy that combining driving style and theory of games
CN110362910A (en) * 2019-07-05 2019-10-22 西南交通大学 Automatic driving vehicle lane-change conflict coordination method for establishing model based on game theory
CN110962853A (en) * 2019-11-25 2020-04-07 浙江工业大学 Vehicle game lane change cooperation method in Internet of vehicles environment
CN111311947A (en) * 2020-03-02 2020-06-19 清华大学 Driving risk assessment method and device considering driver intention in internet environment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
马媛媛: ""基于博弈论的网联车辆换道辅助决策方法研究"", 《中国优秀硕士学位论文全文数据库（电子期刊）》 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113942504A (en) * 2020-07-16 2022-01-18 华为技术有限公司 Self-adaptive cruise control method and device
WO2022134711A1 (en) * 2020-12-24 2022-06-30 华为技术有限公司 Driving style recognition method, assisted driving method, and apparatuses
CN112907967A (en) * 2021-01-29 2021-06-04 吉林大学 Intelligent vehicle lane change decision-making method based on incomplete information game
CN113096379A (en) * 2021-03-03 2021-07-09 东南大学 Driving style identification method based on traffic conflict
CN113282413A (en) * 2021-05-20 2021-08-20 南京航空航天大学 QoS demand self-adaptive resource allocation method in vehicle edge computing network
CN113282413B (en) * 2021-05-20 2024-03-05 南京航空航天大学 QoS demand self-adaptive resource allocation method in vehicle edge computing network
CN113200056A (en) * 2021-06-22 2021-08-03 吉林大学 Incomplete information non-cooperative game man-machine co-driving control method
CN113516846A (en) * 2021-06-24 2021-10-19 长安大学 Vehicle lane change behavior prediction model construction, prediction and early warning method and system
CN113516846B (en) * 2021-06-24 2022-12-13 长安大学 Vehicle lane change behavior prediction model construction, prediction and early warning method and system
CN114882705A (en) * 2022-05-30 2022-08-09 武汉理工大学 Freight vehicle interactive game lane change decision-making method based on lane change decision-making system
CN114882705B (en) * 2022-05-30 2024-04-26 武汉理工大学 Freight vehicle interactive game lane change decision method based on lane change decision system
CN114919578A (en) * 2022-07-20 2022-08-19 北京理工大学前沿技术研究院 Intelligent vehicle behavior decision method, planning method, system and storage medium

Similar Documents

Publication Publication Date Title
CN111994079A (en) Non-cooperative game lane change auxiliary decision making system and method considering driving style characteristics
CN108595823B (en) Autonomous main vehicle lane changing strategy calculation method combining driving style and game theory
CN109345020B (en) Non-signalized intersection vehicle driving behavior prediction method under complete information
CN111081065B (en) Intelligent vehicle collaborative lane change decision model under road section mixed traveling condition
CN111104969B (en) Collision possibility pre-judging method for unmanned vehicle and surrounding vehicles
CN112307566B (en) Vehicle simulation test method, device, equipment and storage medium
CN110007675B (en) Vehicle automatic driving decision-making system based on driving situation map and training set preparation method based on unmanned aerial vehicle
CN109334563B (en) Anti-collision early warning method based on pedestrians and riders in front of road
EP3882095A1 (en) Method and device for determining vehicle speed
CN112347567A (en) Vehicle intention and track prediction method
CN107168303A (en) A kind of automatic Pilot method and device of automobile
CN111178213A (en) Aerial photography vehicle detection method based on deep learning
CN111667512A (en) Multi-target vehicle track prediction method based on improved Kalman filtering
CN113516846B (en) Vehicle lane change behavior prediction model construction, prediction and early warning method and system
WO2023231569A1 (en) Bayesian-game-based vehicle-road cooperative decision-making algorithm for lane changing behavior of autonomous vehicle
CN111968372A (en) Multi-vehicle type mixed traffic following behavior simulation method considering subjective factors
CN112201070B (en) Deep learning-based automatic driving expressway bottleneck section behavior decision method
CN113743469A (en) Automatic driving decision-making method fusing multi-source data and comprehensive multi-dimensional indexes
CN114987498A (en) Anthropomorphic trajectory planning method and device for automatic driving vehicle, vehicle and medium
CN113424209B (en) Trajectory prediction using deep learning multi-predictor fusion and Bayesian optimization
CN114169444B (en) Driving style classification method considering risk potential field distribution under vehicle following working condition
CN114492043A (en) Personalized driver following modeling method considering perception limited characteristics
Eggert et al. The foresighted driver: Future ADAS based on generalized predictive risk estimation
CN112172829B (en) Lane departure warning method and device, electronic equipment and storage medium
CN113761715B (en) Method for establishing personalized vehicle following model based on Gaussian mixture and hidden Markov

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20201127

RJ01 Rejection of invention patent application after publication