CN111199284A - Vehicle-vehicle interaction model under condition of manned and unmanned mixed driving - Google Patents
Vehicle-vehicle interaction model under condition of manned and unmanned mixed driving Download PDFInfo
- Publication number
- CN111199284A CN111199284A CN201911297888.9A CN201911297888A CN111199284A CN 111199284 A CN111199284 A CN 111199284A CN 201911297888 A CN201911297888 A CN 201911297888A CN 111199284 A CN111199284 A CN 111199284A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- lane
- interaction
- driving
- collision
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/048—Fuzzy inferencing
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
Abstract
The invention relates to a vehicle-vehicle interaction model under the condition of man-in-vehicle and unmanned mixed driving, which is characterized in that the driving states of unmanned vehicles and manned vehicles are obtained based on an environment sensing module, a vehicle interaction relation judgment model is established by fuzzy reasoning, unmanned vehicle decision is carried out according to the obtained prediction result, the driving interaction behaviors among vehicles are divided into two categories of road section interaction and intersection interaction, then a fuzzy logic method is applied to establish a vehicle lane changing interaction relation judgment model and a vehicle crossing interaction relation judgment model, the model comprehensively considers the lane changing (crossing) intention of two interaction parties and the types of other vehicle drivers, the degree of cooperation competition among fuzzy reasoning vehicles is established, the mapping relation between a fuzzy reasoning output value and an interaction relation prediction result is established, and the vehicle-vehicle interaction behavior under the mixed driving condition is analyzed to help the unmanned vehicles to understand, And judging the behavior of the peripheral manned vehicle.
Description
Technical Field
The invention belongs to the technical field of intelligent traffic, and particularly relates to a vehicle-vehicle interaction model under the condition of manned and unmanned mixed traffic.
Background
The development of unmanned technology has become a global consensus, and has great potential in solving traffic safety and treating traffic congestion. The department of transportation in the united states of america in 2014 proposes "ITS strategic plan 2015-. The european union committee proposed the "GEAR 2030 strategy" in 2015, focusing on the advancement and cooperation in the fields of highly automated and networked driving. The intelligent networked automobile is further developed and applied in the directions of networked cooperative sensing, networked cooperative decision and control, conditional automatic driving, full automatic driving and the like.
Although the research on the unmanned vehicle related art has made great progress, enabling low-speed driving in a limited area of an urban road, and autonomous driving in a simple environment of an expressway, the application of unmanned in the automotive field is also becoming problematic, so that people are still in worry and apprehension about the unmanned technology. According to statistics of road safety records of manned and unmanned vehicles by the university of michigan in traffic research, research shows that unmanned vehicles are more prone to accidents than manned vehicles, the accident ratio of the unmanned vehicles to the manned vehicles is 9.1:1.9, and the rear-end collision accident ratio of the unmanned vehicles is 50% higher than that of the manned vehicles. For example, in 2016, a traffic accident occurred in Tesla Model S with automated driving enabled in California, USA, which was the earliest reported traffic accident due to automated driving program errors. In 2018, in 3 months, a Uber unmanned test vehicle crashed into a pedestrian in arizona to cause death, which is the death accident caused by the pedestrian being crashed together with the automatic driving vehicle, and after the accident, the Uber suspended the automatic driving test work. Therefore, the automatic driving function is not mature, and the decision control system still has potential safety hazards.
In addition, in the united states DARPA urban challenge race, "chinese intelligent vehicle future challenge race (IVFC)", "chinese intelligent vehicle race (CIVC)", "world intelligent driving challenge race (WIDC)", when facing the interference of the manned vehicles, the racing vehicles mostly adopt the conservative driving behaviors of deceleration or waiting to avoid conflict, the influence of the dynamic interactive behaviors of other vehicles is not considered, the difference influence of the interactive behaviors of different types of drivers is ignored, and the cross traffic potential of the unmanned vehicles is greatly limited.
At present, the intelligent degree of an automobile has realized completely automatic driving under a limited condition, the automation level basically reaches the level of L3, but the unmanned level at the level of L4 and L5 has a certain distance, so that the unmanned vehicle is going to be driven on the road really in the future and is about to face a mixed traffic environment coexisting with a manned vehicle, and therefore the unmanned vehicle is required to have an effective interaction mechanism, cooperative driving of the manned vehicle and the unmanned vehicle is realized in the mixed driving environment, and the advantages of accurate control and internet communication and the like are fully exerted.
Aiming at the problems, when a person and an unmanned automobile share the road resources, the road resources can be effectively utilized only by realizing the interactive cooperation of the person and the unmanned automobile, and traffic accidents are prevented. The research combines the research of the national key research and development plan subject 'quantitative evaluation technology research of the environmental adaptability of the automatically-driven electric automobile', and establishes a road section vehicle lane changing interactive relation judgment model and an intersection crossing interactive relation judgment model by taking a vehicle-vehicle interactive relation under the condition that people and unmanned vehicles are mixed to run as a key link of safe interactive driving, and the road section vehicle lane changing interactive relation judgment model and the intersection crossing interactive relation judgment model are expressed by vehicle cooperation competition degrees to help the unmanned vehicles to understand and judge the behaviors of the people and the vehicles around.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a vehicle-vehicle interaction model under the condition of manned and unmanned mixed driving. The method comprises the steps of establishing a vehicle lane changing interactive relation and a vehicle crossing interactive relation judgment model based on a fuzzy logic method, comprehensively considering the lane changing (crossing) intention of two interactive parties and the types of drivers of other vehicles and carrying out fuzzy reasoning on the cooperation competition degree among the vehicles, establishing a mapping relation between a fuzzy reasoning output value and an interactive relation prediction result, analyzing the vehicle-vehicle interactive behavior under the mixed condition, helping the unmanned vehicle to understand and judge the behavior of the peripheral vehicles, and laying a foundation for realizing multi-vehicle cooperative driving.
The technical scheme adopted by the invention is as follows:
a vehicle-vehicle interaction model under the condition of man-in-vehicle and unmanned mixed driving is characterized in that driving states of unmanned vehicles and manned vehicles are obtained based on an environment sensing module, a vehicle interaction relation judgment model is built through fuzzy reasoning, unmanned vehicle decision is made according to the obtained prediction result, driving interaction behaviors among vehicles are divided into two categories of road section interaction and intersection interaction, then a vehicle lane changing interaction relation judgment model and a vehicle crossing interaction relation judgment model are built through a fuzzy logic method, the model comprehensively considers the lane changing (crossing) intention of two interaction parties and the types of other vehicle drivers, the degree of cooperation competition among fuzzy reasoning vehicles is built, the mapping relation between a fuzzy reasoning output value and an interaction relation prediction result is built, the vehicle-vehicle interaction behaviors under the mixed driving condition are analyzed, and the unmanned vehicles are helped to understand, And judging the behavior of the peripheral manned vehicle.
Moreover, the vehicle lane change interactive relationship determination model is divided into two steps when establishing the vehicle lane change interactive relationship determination model by combining understanding of lane change behavior interactive characteristics: the first step is to judge the level of the lane change intention of the target vehicle on the original lane; and the second step is to judge the driving type of the vehicle carried behind the target lane, and the interactive relation between the vehicles is deduced by combining the two steps to show the cooperation degree between the vehicles.
In the course of judging the lane change will of the target vehicle on the original lane, the main judgment criteria for lane change of the vehicle is whether a better driving space can be obtained under the condition of meeting the safety, the driving benefit △ Db increased after lane change of the vehicle and the conflict degree Tc with the vehicle behind the target lane are used as model input quantities, the level of the lane change will is used as an output variable, and the driving benefit difference is expressed by delta Db, and the formula is as follows:
ΔDb＝Dbi-Dbj
Dbi＝(vPV(t)-vSV(t)+Li(t))·α1
Dbj＝(vTPV(t)-vSV(t)+Lj(t))·α2
in the formula:
Dbi-the original lane driving benefit;
Dbj-a target lane driving benefit;
vSV(t) -target vehicle speed (m/s);
vPV(t) -speed (m/s) ahead of the original lane target vehicle;
vTPV(t) -target lane front speed (m/s);
Li(t) -the distance (m) of the target vehicle from the vehicle ahead of the original lane;
Lj(t) -distance (m) of the target vehicle from the vehicle in front of the target lane;
α1-correction factor of the front vehicle of the original lane;
α2-correction factor of the vehicle ahead of the target lane.
And (3) constructing a driving benefit difference membership function by combining the measured data and the existing research, setting the theoretical domain range of the lane driving benefit difference △ Db as {0, 5, 10, 15, 20}, and setting the fuzzy set as { Very Small (VS), small (S), medium (M), large (L) and Very Large (VL) }.
Moreover, the Collision severity Tc is not immediately executed when the lane change operation is not executed after the vehicle has made a lane change intention, and further determines whether a lane change safety condition is satisfied, where TTc (Time to Collision, TTc) represents the severity of the Collision with the rear vehicle in the target lane, and is denoted as Tc, and the Collision point in the rear-end Collision is the contact between the front vehicle head and the front vehicle tail, so the vehicle length should be considered in calculating TTc, and the calculation formula is:
in the formula:
xSV(t) -the current position (m) of the target vehicle SV;
xTFV(t) -the current position (m) of the vehicle TFV behind the target lane;
vSV(t) -target vehicle FV speed (m/s);
vTFV(t) -TFV speed (m/s) of the vehicle behind the target lane;
l- -vehicle body length (m).
Further, the scope of the severity Tc of the collision between the target vehicle and the vehicle behind the target lane is set to {0, 3, 5, 7, 10} and the fuzzy set is { large (VL), large (L), medium (M), small (S), small (VS) }, according to the above analysis, as the lane driving benefit value △ Db is larger, the collision Tc between the host vehicle and the vehicle behind the target lane is smaller, the vehicle is more likely to select lane change to pursue better driving conditions, and conversely, as the lane driving benefit value △ Db is smaller, the collision Tc with the vehicle behind the target lane is larger, the possibility of lane change of the driver is smaller.
And, according to the level of the target vehicle lane change intention and the driving type of the vehicle behind the target lane, the level of the lane change intention and the type of the driver of the other vehicle are used as input variables, the output is the level of the vehicle cooperation competition degree, the values of the vehicle cooperation degree are expressed by language variables of high (H), medium (M) and low (L), and the results are 3 results of cooperation relation, ambiguous and competition relation respectively corresponding to the interaction relation of the other vehicle.
Whether the vehicle can cross the intersection is mainly related to the collision pressure and the collision severity sensed by the vehicle, the intersection collision pressure P and the collision severity Tc are used as model input quantities, the output variable is the crossing willingness degree, the effective communication range of the vehicle entering the intersection is set to be 150m, the collision pressure is set to be 0, the pressure reaching the conflict point is set to be 1, and the collision pressure expression is as follows:
in the formula:
p-conflict pressure;
Li(t) -distance (m) of ith vehicle from the conflict point
The intersection conflict pressure P and the conflict severity Tc are used as model input quantities, the output variable is the crossing desire level, a conflict pressure membership function is constructed, the domain range of the conflict pressure P is set to be {0.1, 0.3, 0.5, 0.7 and 0.9}, and the fuzzy set is { Very Small (VS), small (S), medium (M), large (L) and Very Large (VL) }.
And whether the target vehicle passes through or not needs to consider the possibility of collision with the collision vehicle, Tc is used for evaluating the danger degree of the vehicle collision at the intersection, and if the collision points or the collision surfaces exist among the traffic participants, the time difference of the passing of the collision points or the collision surfaces is TcExpressed by the following formula:
in the formula:
LCSV(t) -distance (m) of the target vehicle CSV from the conflict point;
LCFV(t) -the distance (m) of the colliding vehicle CFV from the conflict point;
vCSV(t) -speed of target vehicle CSV (m/s);
vCFV(t) -speed of conflicting vehicle CFV (m/s)
Combining the measured data and the existing research, the domain scope set as the domain scope of the conflict severity Tc is set as {0, 3, 5, 7, 10}, and the fuzzy set is { Very Large (VL), large (L), medium (M), small (S), Very Small (VS) }.
Moreover, when the collision pressure P is larger and the collision severity Tc is smaller, the more likely the driver is to choose to cross over to obtain better driving conditions; conversely, the smaller the collision pressure P, the greater the collision severity Tc, and the less likely the driver will cross.
And calculating to obtain the corresponding relation between the vehicle cooperation competition degree, the traversing intention and the driving type, defuzzifying the fuzzy inference output value, expressing the output value of the vehicle cooperation degree by p, wherein the p is a value between 0 and 1, the lower the quantized value of p is, the stronger the competition among the vehicles is, and conversely, the higher the quantized value of p is, the higher the cooperation degree among the vehicles is, and establishing the mapping relation between the fuzzy inference output value and the interactive relation prediction result as follows:
wherein 3 represents cooperation, 2 represents an undefined state, 1 represents competition, and vehicle-vehicle interaction behaviors under mixed conditions are analyzed through prediction of vehicle interaction relations, so that the unmanned vehicle is helped to understand and judge the behaviors of the vehicles with the people around.
The invention has the advantages and positive effects that:
establishing a vehicle lane change interactive relation judgment model and an intersection crossing interactive relation judgment model based on a fuzzy logic method to analyze vehicle-vehicle interactive behaviors under mixed-driving conditions, and helping an unmanned vehicle to understand and judge the behavior of a peripheral vehicle; and several groups of road section and intersection driving data under the mixed running condition in the Chinese intelligent automobile competition are selected as input parameters of the model, the effectiveness of the vehicle lane changing interactive relationship and intersection crossing interactive relationship judgment model is verified, and the result shows that the accuracy of the fuzzy reasoning method for predicting the cooperative competition degree in the vehicle lane changing and intersection crossing process exceeds 87.3% and 91.6%, the more extreme the vehicle cooperation and competition degree is, the higher the accuracy is, the unmanned vehicle has the capability of understanding human behaviors, and the foundation is laid for realizing multi-vehicle cooperative driving.
Drawings
FIG. 1 is a diagram of vehicle-vehicle interaction under mixed manned and unmanned vehicle conditions in accordance with the present invention;
FIG. 2 is a schematic diagram illustrating a vehicle lane change interaction relationship determination in the present invention;
FIG. 3 is a driving benefit difference membership function graph for vehicle lane change interaction determination in accordance with the present invention;
FIG. 4 is a membership function graph of the severity of conflict when a lane change interaction relationship of a vehicle is determined in the present invention;
FIG. 5 is a graph of a membership function of the following speed of a target lane when a vehicle crosses an interactive relationship in the present invention;
FIG. 6 is a graph of a vehicle-following acceleration membership function of a target lane during determination of a vehicle crossing interaction relationship in the present invention;
FIG. 7 is a schematic diagram illustrating a vehicle crossing interaction relationship determination in accordance with the present invention;
FIG. 8 is a graph of a collision pressure membership function as determined by vehicle cross interaction in accordance with the present invention;
FIG. 9 is a graph of membership function for collision severity in determining vehicle cross-interaction relationship in accordance with the present invention;
FIG. 10 is a graph illustrating a predicted result of interaction between vehicles driving along a lane change data sample road segment in accordance with an exemplary embodiment;
fig. 11 is a diagram of a result of predicting an interaction relationship between crossing vehicles at an intersection in the specific embodiment.
Detailed Description
The present invention will be described in further detail with reference to the following embodiments, which are illustrative only and not limiting, and the scope of the present invention is not limited thereby.
A vehicle-vehicle interaction model under the condition of man-in-man and unmanned mixed running is disclosed, as shown in figure 1, the running states of unmanned vehicles and manned vehicles are obtained based on an environment sensing module, a vehicle interaction relation judgment model is established by fuzzy reasoning, unmanned vehicle decision is carried out according to the obtained prediction result, the driving interaction behaviors among vehicles are divided into two categories of road section interaction and intersection interaction, then a vehicle lane change interaction relation judgment model and a vehicle crossing interaction relation judgment model are established by a fuzzy logic method, the model comprehensively considers the lane change (crossing) intention of two interaction parties and the types of other vehicle drivers, the cooperation competition degree among the fuzzy reasoning vehicles, the mapping relation between a fuzzy reasoning output value and an interaction relation prediction result is established, so as to analyze the vehicle-vehicle interaction behaviors under the mixed running condition, the unmanned vehicle is helped to understand and judge the behavior of the vehicles with people in the periphery.
As shown in fig. 2, the vehicle lane change interaction relationship determination model is divided into two steps when establishing the vehicle lane change interaction relationship determination model by combining understanding of lane change behavior interaction characteristics: the first step is to judge the level of the lane change intention of the target vehicle on the original lane; and the second step is to judge the driving type of the vehicle behind the target lane. And the interactive relation between the vehicles is deduced by combining the two steps, so that the degree of cooperation between the vehicles is represented.
Judging the level of the lane change will of the target vehicle in the original lane
The main judgment criteria for the lane change of the vehicle is whether a better Driving space can be obtained under the condition of meeting safety, the Driving Benefit (Driving Benefit) △ Db added after the lane change of the vehicle and the collision degree Tc with the vehicle behind the target lane are used as model input quantities, and the degree of the lane change will is used as an output variable.
Model variables and membership functions
The level of the lane change will of the target vehicle is generally related to the following two factors:
(1) benefits of driving
The lane change behavior aims to improve the driving benefit of the lane change behavior, the lane change demand is more intense when the driving benefit increased after the lane change of the target vehicle is larger, the lane change intention is generated due to the difference of the driving benefits of the target lane and the original lane, and the lane change intention of the driver is stronger when the difference of the benefits is larger.
The driving benefit difference is represented by Δ Db, and its formula is as follows:
ΔDb＝Dbi-Dbj
Dbi＝(vPV(t)-vSV(t)+Li(t))·α1
Dbj＝(vTPV(t)-vSV(t)+Lj(t))·α2
in the formula:
Dbi-the driving interests of the original lane;
Dbi-a target lane driving benefit;
vSV(t) -target vehicle speed (m/s);
vPV(t) -speed (m/s) ahead of the original lane target vehicle;
vTPV(t) -target lane front speed (m/s);
Li(t) -the distance (m) of the target vehicle from the vehicle ahead of the original lane;
Lj(t) -distance (m) of the target vehicle from the vehicle in front of the target lane;
α1-correction factor of the front vehicle of the original lane;
α2-correction factor of the vehicle ahead of the target lane.
The driving benefit difference membership function is constructed by combining measured data and the existing research, the domain range of the lane driving benefit difference delta Db is set as {0, 5, 10, 15 and 20}, the fuzzy set is { Very Small (VS), small (S), medium (M), large (L) and Very Large (VL) }, and the driving benefit difference membership function is shown in FIG. 3.
(2) Severity of conflict
Tc, when the vehicle generates the lane change intention, the lane change operation is not executed immediately, and it is further determined whether the lane change safety condition is satisfied. In this chapter, the severity of the Collision with the rear vehicle of the target lane is denoted by TTC (Time to Collision, TTC), and is denoted as Tc. In the rear-end collision, the collision point is that the rear vehicle head contacts with the front vehicle tail, so the vehicle body length should be considered when calculating the TTC, and the calculation formula is as follows:
in the formula:
xSV(t) -the current position (m) of the target vehicle SV;
xTFV(t) -the current position (m) of the vehicle TFV behind the target lane;
vSV(t) -target vehicle FV speed (m/s);
vTFV(t) -TFV speed (m/s) of the vehicle behind the target lane;
l-vehicle body length (m).
The domain scope of the severity Tc of the rear vehicle conflict between the target vehicle and the target lane is taken as {0, 3, 5, 7, 10} by combining the measured data and the existing research, and the fuzzy set is { Very Large (VL), large (L), medium (M), small (S) and Very Small (VS) }. The severity of the collision, Tc, is a membership function as shown in FIG. 4.
Fuzzy control rule
The lane change will high and low degrees are expressed by language variables of extremely low (PL), low (L), medium (M), high (H) and extremely high (PH), so that the fuzzy rule of the lane change will of the vehicle is determined as shown in the table 1.
TABLE 1 fuzzy logic rule table of lane change willingness
From the above analysis, it is found that the larger the lane driving benefit value △ Db is, the smaller the vehicle collision Tc with the vehicle behind the target lane is, the more likely the vehicle will select a lane change to pursue better driving conditions, whereas the smaller the lane driving benefit value △ Db is, the larger the collision Tc with the vehicle behind the target lane is, the less likely the driver will change lanes.
Type of driving behind target lane
When the target vehicle generates the lane change intention, the intention of the vehicle to accept or reject the lane change request is different for different driver types and vehicles behind the target lane. Such as more conservative drivers being more likely to give way or compromise, and more aggressive drivers being more likely to give way to other vehicles, the driver type of the other vehicle is therefore closely related to the vehicle interaction.
Human drivers can be divided into an aggressive type, a common type and a conservative type according to the driving aggressive degree of the human drivers, the vehicle speed and the acceleration are used as model input quantities, the driving aggressive degree is used as a model output quantity, and a fuzzy logic rule is constructed.
The speed and acceleration input values are obtained by the following two formulas:
wherein v isi、aiRespectively representing the velocity, acceleration, N at time ivAnd N are the time times corresponding to the received speed and acceleration information respectively.
Combining measured data and the existing research, taking the domain range of the speed of the target vehicle behind as {5, 10, 15, 20, 25}, and taking the fuzzy set as { Very Small (VS), small (S), medium (M), large (L), Very Large (VL) }; the domain of absolute value of acceleration is taken as {1, 2, 3}, and the fuzzy set is { small (S), medium (M), large (L) } velocity, acceleration membership function is shown in fig. 5 and 6.
And determining the fuzzy rules of the types of drivers of other vehicles according to an expert experience method and an observation method, wherein the driving motivation degrees are respectively expressed by linguistic variables of motivation (A), common (N) and conservation (C), and are shown in a table 2.
TABLE 2 fuzzy logic rules Table
Fuzzy inference
According to the level of the lane change intention of the target vehicle and the driving type of the vehicle behind the target lane, the level of the lane change intention and the type of the driver of the other vehicle are used as input variables, the output is the level of the vehicle cooperation competition degree, the values of the vehicle cooperation degree are expressed by language variables of high (H), medium (M) and low (L), the fuzzy logic rules of the vehicle lane change interaction relationship are respectively corresponding to 3 results of the other vehicle interaction relationship, namely the cooperation relationship, the ambiguity and the competition relationship, and are shown in a table 3.
TABLE 3 fuzzy logic rule table of interaction relation for changing lane of vehicle
The fuzzy implication relations of the partial fuzzy reasoning adopt a Mamdani rule, the ambiguity resolution adopts a gravity center method, and the corresponding relation between the vehicle cooperation competition degree, the lane change will and the driving type is obtained through calculation.
As shown in fig. 7, the vehicle crossing interactive relationship determination model is established according to the crossing will of the target vehicle at the intersection and the driving types of the conflicting vehicles, and the degree of cooperation between the vehicles is inferred by using a fuzzy logic method.
Level of target vehicle crossing will
Whether the vehicle can cross the intersection is mainly related to the collision pressure and the collision severity sensed by the vehicle, the intersection collision pressure P and the collision severity Tc are used as model input quantities, and the output variable is the crossing willingness degree.
The level of the crossing target vehicle's willingness to cross is generally related to two factors:
(1) generally, the conflict pressure P may cause traffic conflicts at intersections due to traffic regulations, for example, straight vehicles and left-turning vehicles may form cross conflicts, and a coincidence area is generated on a spatial trajectory, which is very likely to cause traffic accidents. Therefore, the vehicles that generate the conflict need to adjust the time for passing through the overlapping area, so as to resolve the conflict. As the driver approaches the conflict point, the sensed conflict pressure increases, and the desire to cross the intersection as soon as possible also increases with increasing pressure, increasing the probability of crossing.
To better describe the magnitude of the collision pressure, assuming that the vehicle enters the intersection effective communication range at 150m, the collision pressure is set to 0 here, the pressure to the collision point is set to 1, and the collision pressure expression is:
in the formula:
p-conflict pressure;
Li(t) — the distance (m) of the ith vehicle from the conflict point.
And taking the intersection conflict pressure P and the conflict severity Tc as model input quantities, and taking output variables as the crossing willingness degree. Constructing a collision pressure membership function, setting the domain scope of the collision pressure P as {0.1, 0.3, 0.5, 0.7, 0.9}, setting the fuzzy set as { Very Small (VS), small (S), medium (M), large (L), Very Large (VL) }, and setting the collision pressure membership function as shown in FIG. 8.
(2) The collision severity Tc whether the target vehicle passes through or not needs to consider the possibility of collision with the colliding vehicle, the risk degree of collision of the vehicles at the intersection is evaluated by Tc, and if there is a colliding point or surface between the traffic participants, the time difference passing through the colliding point or surface is Tc, which is expressed by the following formula:
in the formula:
LCSV(t) -distance (m) of the target vehicle CSV from the conflict point;
LCFV(t) -the distance (m) of the colliding vehicle CFV from the conflict point;
vCSV(t) -speed of target vehicle CSV (m/s);
vCFV(t) -speed of conflicting vehicle CFV (m/s).
Combining the measured data and the existing research, the domain scope set as the domain scope of the conflict severity Tc is set as {0, 3, 5, 7, 10}, and the fuzzy set is { Very Large (VL), large (L), medium (M), small (S), Very Small (VS) }. The collision severity Tc membership function is shown in fig. 9.
The fuzzy control rule is known from the analysis, when the conflict pressure P is larger and the conflict severity Tc is smaller, the driver is more likely to select to pass through to obtain better driving conditions; conversely, the smaller the collision pressure P, the greater the collision severity Tc, and the smaller the driver's ride-through possibility, thereby determining the vehicle ride-through will fuzzy rule as shown in table 4.
TABLE 4 traversing will fuzzy logic rule Table
Driving type of conflicting vehicle
For vehicles passing through the intersection, the willingness of the vehicles to select to accept or reject the crossing request is different for different driver types, and the fuzzy logic construction method of the conflicting vehicle driving types is similar to the construction method of other vehicle driver types in the lane changing. Fuzzy rules for determining conflicting vehicle driving types based on expert experience and observation are shown in table 5.
TABLE 5 fuzzy logic rules Table
And (4) taking the traversing intention of the target vehicle and the types of drivers of other vehicles obtained in the two steps as input variables, outputting the input variables as the cooperation degree of the vehicle traversing and traversing, and constructing a vehicle traversing interactive relation judgment model. The vehicle cooperation degree values are expressed by language variables of high (H), medium (M) and low (L), and correspond to 3 results that the other vehicle interaction relationships are cooperation relationships, ambiguous relationships and competitive relationships respectively, and the vehicle-crossing interaction relationship fuzzy logic rule is shown in table 6.
TABLE 6 fuzzy logic rule table for vehicle crossing interaction relation
Similarly, the fuzzy implication relations of the partial fuzzy reasoning adopt a Mamdani rule, the ambiguity resolution adopts a gravity center method, the corresponding relation between the vehicle cooperation competition degree, the traversing intention and the driving type is obtained through calculation, the fuzzy reasoning output value is subjected to defuzzification processing, and the output value of the vehicle cooperation degree is represented by p. And p takes a value between 0 and 1, the lower the quantized value of p is, the more fierce competition among the vehicles is, and on the contrary, the higher the quantized value of p is, the higher the cooperation degree among the vehicles is. The mapping relationship between the fuzzy inference output value and the interactive relationship prediction result is established as follows:
where 3 denotes a cooperative relationship, 2 denotes an ambiguous state, and 1 denotes a competitive relationship. Through the prediction of the vehicle interaction relation, the vehicle-vehicle interaction behavior under the mixed-driving condition is analyzed, and the unmanned vehicle is helped to understand and judge the behavior of the people around the unmanned vehicle.
As shown in fig. 10, 150 sets of real road segment lane change data samples are selected for vehicle cooperation and competition degree classification, wherein 3 is cooperation relationship and represents the yielding intention of other vehicles, 2 is ambiguous and represents the uncertain state of other vehicles, and 1 is competition relationship and represents the failing intention of other vehicles. From the prediction results in the figure, it can be seen that the model correctly identifies 48 samples of the cooperative relationship, 38 samples of the ambiguous state, 45 samples of the competitive relationship, and a total of 131 correctly identified samples, and the prediction accuracy is 87.3%. The more extreme the vehicle cooperation competition degree is, the higher the accuracy is, the accuracy of the prediction result 1 or 3 exceeds 90%, which shows that the unmanned vehicle has the capability of understanding human behaviors, and lays a foundation for the cooperation of the unmanned vehicle and the manned vehicle.
As shown in fig. 11, 120 sets of intersection crossing data samples are selected to classify the degree of vehicle cooperation and competition, where 3 is a cooperation relation indicating the intention of the other vehicle to yield, 2 is an ambiguity indicating the uncertain state of the other vehicle, and 1 is a competition relation indicating the intention of the other vehicle to not yield. From the figure, it is understood that 38 samples of cooperation relationship, 35 samples of undefined state and 37 samples of competition relationship are correctly identified by the model, and the total number of correct identifications is 110, and the detection accuracy is 91.6%. The accuracy of the fuzzy inference method for predicting the cooperation degree of the vehicle exceeds 90%, which shows that the unmanned vehicle has the capability of understanding human behaviors and lays a foundation for the cooperation of the unmanned vehicle and the manned vehicle.
Although the embodiments of the present invention and the accompanying drawings are disclosed for illustrative purposes, those skilled in the art will appreciate that: various substitutions, changes and modifications are possible without departing from the spirit and scope of the invention and the appended claims, and therefore the scope of the invention is not limited to the disclosure of the embodiments and the accompanying drawings.
Claims (10)
1. A vehicle-vehicle interaction model under the condition of manned and unmanned mixed running is characterized in that: the method comprises the steps of obtaining driving states of unmanned vehicles and manned vehicles based on an environment sensing module, establishing a vehicle interaction relation judgment model by fuzzy reasoning, carrying out unmanned vehicle decision making according to a prediction result obtained by the vehicle interaction relation judgment model, dividing driving interaction behaviors among the vehicles into two categories of road section interaction and intersection interaction, then establishing a vehicle lane changing interaction relation judgment model and a vehicle crossing interaction relation judgment model by a fuzzy logic method, comprehensively considering lane changing (crossing) intention levels of two interaction parties and other vehicle driver types, and carrying out fuzzy reasoning on the cooperation competition degree among the vehicles, establishing a mapping relation between a fuzzy reasoning output value and an interaction relation prediction result, so as to analyze vehicle-vehicle interaction behaviors under a mixed condition, and helping the unmanned vehicles to understand and judge the behaviors of the peripheral manned vehicles.
2. The vehicle-vehicle interaction model under manned and unmanned mixed-driving conditions of claim 1, characterized in that: the vehicle lane change interactive relationship determination model is divided into two steps when the vehicle lane change interactive relationship determination model is established by combining understanding of lane change behavior interactive characteristics: the first step is to judge the level of the lane change intention of the target vehicle on the original lane; and the second step is to judge the driving type of the vehicle carried behind the target lane, and the interactive relation between the vehicles is deduced by combining the two steps to show the cooperation degree between the vehicles.
3. The vehicle-vehicle interaction model under the manned and unmanned mixed driving condition as claimed in claim 2, wherein in the process of judging the lane change will of the target vehicle in the original lane, the main judgment criteria for lane change of the vehicle is whether a better driving space can be obtained under the condition of meeting the safety, the driving benefit △ Db increased after lane change of the vehicle and the conflict degree Tc with the vehicle behind the target lane are used as model input quantities, the lane change will degree is used as an output variable, the driving benefit difference is represented by △ Db, and the formula is as follows:
ΔDb＝Dbi-Dbj
Dbi＝(vPV(t)-vSV(t)+Li(t))·α1
Dbj＝(vTPV(t)-vSV(t)+Lj(t))·α2
in the formula:
Dbi-the driving interests of the original lane;
Dbj-a target lane driving benefit;
vSV(t) -target vehicle speed (m/s);
vPV(t) -speed (m/s) ahead of the original lane target vehicle;
vTPV(t) -target lane front speed (m/s);
Li(t) -the distance (m) of the target vehicle from the vehicle ahead of the original lane;
Lj(t) -distance (m) of the target vehicle from the vehicle in front of the target lane;
α1-correction factor of the front vehicle of the original lane;
α2-correction factor of the vehicle ahead of the target lane.
And (3) constructing a driving benefit difference membership function by combining the measured data and the existing research, setting the domain scope of the lane driving benefit difference △ Db as {0, 5, 10, 15, 20}, and setting the fuzzy set as { Very Small (VS), small (S), medium (M), large (L) and Very Large (VL) }.
4. The vehicle-vehicle interaction model under manned and unmanned mixed-driving conditions of claim 3, characterized in that: when the lane change intention is generated by the vehicle, the lane change operation is not executed immediately, and whether the lane change safety condition is satisfied needs to be further judged, TTc (Time to Collision, TTc) represents the severity of the rear vehicle Collision with the target lane, which is denoted as Tc, and the Collision point in the rear-end Collision is the contact between the rear vehicle head and the front vehicle tail, so the vehicle length should be considered in calculating TTc, and the calculation formula is as follows:
in the formula:
xSV(t) -the current position (m) of the target vehicle SV;
xTFV(t) -the current position (m) of the vehicle TFV behind the target lane;
vSV(t) -target vehicle FV speed (m/s);
vTFV(t) -TFV speed (m/s) of the vehicle behind the target lane;
l-vehicle body length (m).
5. The vehicle-vehicle interaction model under the mixed manned and unmanned condition as claimed in claim 4, wherein the universe of discourse of the severity Tc of the conflict between the target vehicle and the vehicle behind the target lane is set as {0, 3, 5, 7, 10} in combination with the measured data and the existing research, and the fuzzy sets are { very big (VL), big (L), medium (M), small (S), Very Small (VS) }, and from the above analysis, the vehicle is more likely to select lane change to pursue better driving conditions when the lane driving benefit value △ Db is larger and the conflict Tc between the vehicle and the vehicle behind the target lane is smaller, whereas the smaller the lane driving benefit value △ Db is, the larger the conflict Tc with the vehicle behind the target lane is, the less likely the lane change of the driver is.
6. The vehicle-vehicle interaction model under manned and unmanned mixed-driving conditions of claim 2, characterized in that: according to the level of the lane change intention of the target vehicle and the driving type of the vehicle behind the target lane, the level of the lane change intention and the type of the driver of the other vehicle are used as input variables, the output is the level of the vehicle cooperation competition degree, the values of the vehicle cooperation degree are expressed by language variables of high (H), medium (M) and low (L), and the values correspond to the interaction relationship of the other vehicle and are 3 results of the cooperation relationship, the ambiguity and the competition relationship respectively.
7. The vehicle-vehicle interaction model under manned and unmanned mixed-driving conditions of claim 6, characterized in that: whether the vehicle can cross the intersection is mainly related to the collision pressure and the collision severity sensed by the vehicle, the intersection collision pressure P and the collision severity Tc are used as model input quantities, the output variable is the crossing willingness degree, the intersection collision pressure P and the collision severity Tc are set within the effective communication range of the intersection of 150m vehicles, the collision pressure is set to be 0, the pressure reaching the conflict point is set to be 1, and the expression of the collision pressure is as follows:
in the formula:
p-conflict pressure;
Li(t) -distance (m) of ith vehicle from the conflict point
The intersection conflict pressure P and the conflict severity Tc are used as model input quantities, the output variable is the crossing desire level, a conflict pressure membership function is constructed, the domain range of the conflict pressure P is set to be {0.1, 0.3, 0.5, 0.7 and 0.9}, and the fuzzy set is { Very Small (VS), small (S), medium (M), large (L) and Very Large (VL) }.
8. The vehicle-vehicle interaction model under manned and unmanned mixed-driving conditions of claim 7, characterized in that: whether the target vehicle passes through or not needs to consider the possibility of collision with a collision vehicle, the danger degree of vehicle collision at the intersection is evaluated by Tc, and if a collision point or a collision surface exists among traffic participants, the time difference passing through the collision point or the collision surface is Tc and is represented by the following formula:
in the formula:
LCSV(t) -target vehicle CSV Range rushDistance (m) of salient points;
LCFV(t) -the distance (m) of the colliding vehicle CFV from the conflict point;
vCSV(t) -speed of target vehicle CSV (m/s);
vCFV(t) -speed of conflicting vehicle CFV (m/s)
Combining the measured data and the existing research, the domain scope set as the domain scope of the conflict severity Tc is set as {0, 3, 5, 7, 10}, and the fuzzy set is { Very Large (VL), large (L), medium (M), small (S), Very Small (VS) }.
9. The vehicle-vehicle interaction model under manned and unmanned mixed-driving conditions of claim 8, wherein: when the collision pressure P is larger and the collision severity Tc is smaller, the driver is more likely to choose to pass through to obtain better driving conditions; conversely, the smaller the collision pressure P, the greater the collision severity Tc, and the less likely the driver will cross.
10. The vehicle-vehicle interaction model under manned and unmanned mixed-driving conditions of claim 8, wherein: calculating to obtain a corresponding relation between the vehicle cooperation competition degree and the traversing intention and the driving type, performing defuzzification processing on the fuzzy inference output value, and expressing an output value of the vehicle cooperation degree by using p, wherein the p is a value between 0 and 1, the lower the quantization value of p is, the stronger the competition among the vehicles is, and conversely, the higher the quantization value of p is, the higher the cooperation degree among the vehicles is, and establishing a mapping relation between the fuzzy inference output value and an interactive relation prediction result as follows:
wherein 3 represents cooperation, 2 represents an undefined state, 1 represents competition, and vehicle-vehicle interaction behaviors under mixed conditions are analyzed through prediction of vehicle interaction relations, so that the unmanned vehicle is helped to understand and judge the behaviors of the vehicles with the people around.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911297888.9A CN111199284A (en) | 2019-12-17 | 2019-12-17 | Vehicle-vehicle interaction model under condition of manned and unmanned mixed driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911297888.9A CN111199284A (en) | 2019-12-17 | 2019-12-17 | Vehicle-vehicle interaction model under condition of manned and unmanned mixed driving |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111199284A true CN111199284A (en) | 2020-05-26 |
Family
ID=70746898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911297888.9A Pending CN111199284A (en) | 2019-12-17 | 2019-12-17 | Vehicle-vehicle interaction model under condition of manned and unmanned mixed driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111199284A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112068587A (en) * | 2020-08-05 | 2020-12-11 | 北京航空航天大学 | Man/unmanned aerial vehicle co-converged cluster interaction method based on European 26891bird communication mechanism |
| CN113409567A (en) * | 2021-01-04 | 2021-09-17 | 清华大学 | Traffic assessment method and system for mixed traffic lane of public transport and automatic driving vehicle |
| CN113511222A (en) * | 2021-08-27 | 2021-10-19 | 清华大学 | Scene self-adaptive vehicle interactive behavior decision and prediction method and device |
| CN115457783A (en) * | 2022-08-30 | 2022-12-09 | 重庆长安汽车股份有限公司 | Method and system for traffic, cooperation and cooperation at signal lamp-free intersection |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020082806A1 (en) * | 1995-01-13 | 2002-06-27 | Kaub Alan R. | Traffic safety prediction model |
| EP2950294A1 (en) * | 2014-05-30 | 2015-12-02 | Honda Research Institute Europe GmbH | Method and vehicle with an advanced driver assistance system for risk-based traffic scene analysis |
| CN110298131A (en) * | 2019-07-05 | 2019-10-01 | 西南交通大学 | Automatic Pilot lane-change decision model method for building up under a kind of mixing driving environment |
-
2019
- 2019-12-17 CN CN201911297888.9A patent/CN111199284A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020082806A1 (en) * | 1995-01-13 | 2002-06-27 | Kaub Alan R. | Traffic safety prediction model |
| EP2950294A1 (en) * | 2014-05-30 | 2015-12-02 | Honda Research Institute Europe GmbH | Method and vehicle with an advanced driver assistance system for risk-based traffic scene analysis |
| CN110298131A (en) * | 2019-07-05 | 2019-10-01 | 西南交通大学 | Automatic Pilot lane-change decision model method for building up under a kind of mixing driving environment |
Non-Patent Citations (2)
| Title |
|---|
| 吉文超: "基于驾驶行为分析的城市道路车辆换道模型研究" * |
| 张颖达: "基于NGSIM数据的车辆变道行为博弈模型" * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112068587A (en) * | 2020-08-05 | 2020-12-11 | 北京航空航天大学 | Man/unmanned aerial vehicle co-converged cluster interaction method based on European 26891bird communication mechanism |
| CN113409567A (en) * | 2021-01-04 | 2021-09-17 | 清华大学 | Traffic assessment method and system for mixed traffic lane of public transport and automatic driving vehicle |
| CN113409567B (en) * | 2021-01-04 | 2022-08-05 | 清华大学 | Traffic assessment method and system for mixed traffic lane of public transport and automatic driving vehicle |
| CN113511222A (en) * | 2021-08-27 | 2021-10-19 | 清华大学 | Scene self-adaptive vehicle interactive behavior decision and prediction method and device |
| CN113511222B (en) * | 2021-08-27 | 2023-09-26 | 清华大学 | Scene self-adaptive vehicle interaction behavior decision and prediction method and device |
| CN115457783A (en) * | 2022-08-30 | 2022-12-09 | 重庆长安汽车股份有限公司 | Method and system for traffic, cooperation and cooperation at signal lamp-free intersection |
| CN115457783B (en) * | 2022-08-30 | 2023-08-11 | 重庆长安汽车股份有限公司 | Traffic, cooperation and cooperation method and system for intersection without signal lamp |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111081065B (en) | Intelligent vehicle collaborative lane change decision model under road section mixed traveling condition | |
| CN110992695B (en) | Vehicle urban intersection traffic decision multi-objective optimization method based on conflict resolution | |
| CN111199284A (en) | Vehicle-vehicle interaction model under condition of manned and unmanned mixed driving | |
| CN110488802B (en) | Decision-making method for dynamic behaviors of automatic driving vehicle in internet environment | |
| CN111104969B (en) | Collision possibility pre-judging method for unmanned vehicle and surrounding vehicles | |
| WO2022052406A1 (en) | Automatic driving training method, apparatus and device, and medium | |
| CN110843789B (en) | Vehicle lane change intention prediction method based on time sequence convolution network | |
| CN110077398B (en) | Risk handling method for intelligent driving | |
| CN111746559B (en) | Method and system for predicting lane changing intention of front vehicle | |
| CN112249008B (en) | Unmanned automobile early warning method aiming at complex dynamic environment | |
| CN111209838A (en) | Driving intention-based dynamic identification method for lane change behavior of surrounding vehicles | |
| CN112258841A (en) | Intelligent vehicle risk assessment method based on vehicle track prediction | |
| Zhang et al. | A framework for turning behavior classification at intersections using 3D LIDAR | |
| CN114446049A (en) | Traffic flow prediction method, system, terminal and medium based on social value orientation | |
| CN114932918A (en) | Behavior decision method and system for intelligent internet vehicle to drive under various road conditions | |
| Amini et al. | Development of a conflict risk evaluation model to assess pedestrian safety in interaction with vehicles | |
| Sharma et al. | Kernelized convolutional transformer network based driver behavior estimation for conflict resolution at unsignalized roundabout | |
| Eggert et al. | The foresighted driver: Future ADAS based on generalized predictive risk estimation | |
| CN114228707A (en) | Anti-collision method and system for unmanned vehicle | |
| CN113643542A (en) | Vehicle track prediction method and system under multi-vehicle interaction environment based on ensemble learning | |
| Feng et al. | A fuzzy logic-based approach for humanized driver modelling | |
| CN115107806A (en) | Vehicle track prediction method facing emergency scene in automatic driving system | |
| Miani et al. | Young drivers’ pedestrian anti-collision braking operation data modelling for ADAS development | |
| Zhang et al. | Vehicle driving behavior predicting and judging using LSTM and statistics methods | |
| Benterki et al. | Multi-model and learning-based framework for real-time trajectory prediction |
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 |