CN110920623B - Prediction method for vehicle changing to front of target lane and vehicle behind target lane in automatic driving - Google Patents
Prediction method for vehicle changing to front of target lane and vehicle behind target lane in automatic driving Download PDFInfo
- Publication number
- CN110920623B CN110920623B CN201911242729.9A CN201911242729A CN110920623B CN 110920623 B CN110920623 B CN 110920623B CN 201911242729 A CN201911242729 A CN 201911242729A CN 110920623 B CN110920623 B CN 110920623B
- Authority
- CN
- China
- Prior art keywords
- lane
- vehicle
- changing
- changing vehicle
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- 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
-
- 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
Abstract
The invention discloses a method for predicting the vehicle after changing lane to the front vehicle of a target lane in automatic driving, which obtains the driving state data of the following vehicles in the current sampling period: the lane pre-changing system comprises a pre-lane changing vehicle, a first vehicle in front of a lane where the pre-lane changing vehicle is located, a first vehicle in front of the pre-lane changing vehicle in a target lane, and a first vehicle behind the pre-lane changing vehicle in the target lane; calculating the willingness degree of the pre-lane-changing vehicle after changing the lane to the vehicle ahead of the target lane by combining the acquired driving state data of each vehicle and the lane environment data; when the willingness degree exceeds a willingness degree threshold value, the lane-changing vehicle is predicted to be behind a preceding vehicle changing to the target lane at a future time. The prediction method effectively eliminates the factors that the surrounding vehicles interfere the decision of the vehicle, and improves the certainty factor of the decision of the vehicle; meanwhile, the data analysis calculation amount of a prediction module in the automatic driving system is effectively reduced, the operation difficulty and the operation cost of the automatic driving system are reduced, and the delay time of decision making is effectively improved.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a prediction method for a vehicle before a lane is changed to a target lane in automatic driving.
Background
The automatic driving comprises four modules of prediction, decision, planning and control, wherein the prediction module predicts whether the vehicle will change the lane at the future moment and the lane changing track under the lane changing condition according to the vehicle driving state data and the lane environment data of each lane. The lane change comprises left lane change and right lane change, and the left lane change and the right lane change comprise the steps of changing lanes to the front of a vehicle in a target lane and changing lanes to the back of the vehicle in the target lane. The decision-making module calculates the next expected state of the vehicle according to the prediction output result, the environmental information, the navigation information, the driver behavior module of the vehicle, the vehicle dynamics model and the like of the prediction module; the planning module plans the running track of the vehicle according to the current state and the next expected state; the control module calculates corresponding throttle, brake and steering according to the planned driving track.
Currently, in the automatic driving systems of some internet enterprises and automobile manufacturers, all vehicles of interest (defined as surrounding vehicles which may interfere with the driving of the vehicle) are predicted to default to lane change at a future time. Some vehicles with low willingness degree of lane changing are not excluded from the vehicles, and the willingness degree is the willingness degree of lane changing. The interested vehicles around with low lane change willingness degree can interfere the decision of the vehicle, the calculation amount of data analysis when the vehicle drives each vehicle is increased, and the operation difficulty and the operation cost of the automatic driving system are increased.
Disclosure of Invention
The invention provides a method for predicting after a vehicle changes lane to a vehicle in front of a target lane in automatic driving, which combines the running state data of four vehicles, namely a pre-lane-changing vehicle, a first vehicle in front of the lane where the pre-lane-changing vehicle is located, a first vehicle in front of the pre-lane-changing vehicle in the target lane and a first vehicle in back of the pre-lane-changing vehicle in the target lane, to calculate the willingness degree of the pre-lane-changing vehicle after the vehicle changes lane to the vehicle in front of the target lane, predicts whether the pre-lane-changing vehicle will change lane to the vehicle in front of the target lane at the future moment according to the willingness degree, effectively eliminates the factor that the surrounding vehicles interfere with the decision of the vehicle, and improves the decision reliability of the; meanwhile, the data analysis calculation amount of a prediction module in the automatic driving system is effectively reduced, the operation difficulty and the operation cost of the automatic driving system are reduced, and the delay time of decision making is effectively improved.
In order to solve the above technical problems, the present invention provides a method for predicting after a vehicle has changed lane to a vehicle ahead of a target lane in autonomous driving, comprising the steps of,
acquiring the following running state data of the vehicle in the current sampling period: the lane pre-changing system comprises a pre-lane changing vehicle, a first vehicle in front of a lane where the pre-lane changing vehicle is located, a first vehicle in front of the pre-lane changing vehicle in a target lane, and a first vehicle behind the pre-lane changing vehicle in the target lane;
calculating the willingness degree lambda of the pre-lane-changing vehicle after changing the lane to the vehicle in front of the target lane by combining the acquired driving state data of each vehicle and the lane environment data, wherein lambda is more than or equal to 0 and less than or equal to 1;
when the willingness degree exceeds a willingness degree threshold value, predicting that the pre-lane-changing vehicle will change lanes to be behind a front vehicle of the target lane at a future moment.
In a preferred embodiment of the present invention, further comprising calculating the willingness factor λ comprises,
when the transverse speed of the pre-lane-changing vehicle towards the target lane direction is less than zero and is maintained for a certain time, the willingness degree of the pre-lane-changing vehicle to change the lane to the target lane is zero;
or when the running speed of the first vehicle in front of the pre-lane-changing vehicle in the target lane is lower than the running speed of the first vehicle in front of the lane in which the pre-lane-changing vehicle is located and the first vehicle in front of the pre-lane-changing vehicle in the target lane is located behind the first vehicle in front of the lane in which the pre-lane-changing vehicle is located, the willingness degree of the pre-lane-changing vehicle to change to the target lane is zero.
In a preferred embodiment of the present invention, further comprising calculating the willingness degree λ further comprises,
calculating the willingness degree lambda 1 under the influence of the traffic lane congestion degree;
calculating the transverse speed v of the pre-lane-changing vehicle towards the target lane direction under the condition that the transverse speed of the pre-lane-changing vehicle towards the target lane direction is greater than or equal to zeroy Willingness degree lambda 2 under influence;
calculating the willingness degree lambda 3 under the influence of the longitudinal distance between the pre-lane changing vehicle and a first vehicle in front of the lane where the pre-lane changing vehicle is located;
calculating the willingness degree lambda 4 under the influence of the acceleration of the pre-lane-changing vehicle;
calculating the willingness degree lambda 5 under the influence of the longitudinal distance between a first vehicle in front of the lane where the pre-lane-changing vehicle is located and a first vehicle in front of the pre-lane-changing vehicle in a target lane;
calculating the willingness degree lambda 6 under the influence of the speed ratio of a first vehicle of a target lane in front of a pre-lane-changing vehicle to a first vehicle in front of a lane in which the pre-lane-changing vehicle is located;
λ ═ max { λ 1, λ 2, λ 3, λ 4, λ 5, λ 6} (formula one);
and calculating the willingness degree lambda of the pre-lane-changing vehicle after changing the lane to the front of the target lane according to the formula I.
In a preferred embodiment of the present invention, the method further comprises calculating the willingness factor λ 1 according to formula one,
the rho 1 represents the congestion degree in front of the lane where the pre-lane-changing vehicle is located;
In a preferred embodiment of the present invention, the method further comprises calculating the willingness factor λ 2 according to formula two,
wherein t represents the transverse speed v of the pre-lane-changing vehicle towards the target lane directionyA time for which a certain fixed value lasts;
t1 and t2 respectively represent two fixed time values on the time axis of t.
In a preferred embodiment of the present invention, further comprising calculating the willingness factor λ 3 comprises,
calculating L1 ═ a + B, A ═ S1-S2+ V1 × t1+ D1;
a represents the distance which needs to be kept between the pre-lane changing vehicle and a first vehicle in front of a lane where the pre-lane changing vehicle is located when the pre-lane changing vehicle runs at a running speed V2;
b characterizes the pre-lane change vehicle at deceleration axA travel distance decelerated from the travel speed V1 to the travel speed V2;
l1 is the initial distance between the pre-lane changing vehicle and the first vehicle in front of the lane where the pre-lane changing vehicle is located;
v1 is the running speed of the pre-lane changing vehicle;
v2 is the running speed of the first vehicle in front of the lane where the lane-changing vehicle is located;
s1 is the braking distance from the braking of the pre-lane changing vehicle to the stopping;
s2 is the braking distance from the braking to the stopping of the first vehicle in front of the lane where the lane-changing vehicle is located;
t1the brake reaction time of the pre-lane-change vehicle;
d1 is the safe stopping distance between the pre-lane changing vehicle and the first vehicle in front of the lane where the pre-lane changing vehicle is located when the pre-lane changing vehicle and the first vehicle brake to stop;
when B is equal to (L1-A) less than or equal to 0, the willingness degree lambda 3 is equal to 1;
when B ═ 0 (L1-a) > and V1 ≦ V2, the desirability λ 3 is 0;
when B ═ L1-a) > 0, and V1 > V2, deceleration a of the pre-track vehicle is calculated according to equation twox：
Calculating the willingness degree lambda 3 according to a formula three:
wherein a represents a preset comfort braking deceleration a of the pre-track-changing vehicleThresAnd deceleration axA difference of (d);
k1characterizing deceleration aThresAnd deceleration axThe slope of a straight line of the functional relationship between the difference value of (a) and the willingness degree lambda 3;
a1characterizing deceleration aThresAnd deceleration axA fixed deceleration value on the deceleration axis.
In a preferred embodiment of the present invention, the method further comprises calculating the willingness factor λ 4 according to formula four,
a represents the actual acceleration of the pre-lane-changing vehicle;
k2representing the slope of a straight line of a functional relation between the actual acceleration of the pre-lane-changing vehicle and the willingness degree lambda 4;
A1characterizing pre-track changesA fixed acceleration value on an acceleration axis where the actual acceleration of the vehicle is located;
Δ λ represents the willingness increment of the pre-lane-change vehicle for a certain time period when the actual acceleration exceeds the acceleration threshold.
In a preferred embodiment of the present invention, further comprising calculating the willingness factor λ 5 comprises,
calculating A ═ S1-S2+ V1 ═ t1+ D1;
a represents the distance which needs to be kept between the pre-lane changing vehicle and a first vehicle in front of a lane where the pre-lane changing vehicle is located when the pre-lane changing vehicle runs at a running speed V2;
v1 is the running speed of the pre-lane changing vehicle;
v2 is the running speed of the first vehicle in front of the lane where the lane-changing vehicle is located;
s1 is the braking distance from the braking of the pre-lane changing vehicle to the stopping;
s2 is the braking distance from the braking to the stopping of the first vehicle in front of the lane where the lane-changing vehicle is located;
t1the brake reaction time of the pre-lane-change vehicle;
d1 is the safe stopping distance between the pre-lane changing vehicle and the first vehicle in front of the lane where the pre-lane changing vehicle is located when the pre-lane changing vehicle and the first vehicle brake to stop;
when L1 > a + Δ 1, λ 5 ═ 0;
when L1 is less than or equal to A + delta 1, calculating the willingness degree lambda 5 according to the formula five,
wherein, L1 is the initial distance between the pre-lane changing vehicle and the first vehicle in front of the lane where the pre-lane changing vehicle is located;
x represents the distance along the lane line between a first vehicle in front of the lane where the pre-lane-changing vehicle is located and a first vehicle in front of the pre-lane-changing vehicle in the target lane;
k3representing that a first vehicle in front of a lane where a pre-lane-changing vehicle is located and a target lane are located in pre-changingThe slope of a straight line of a functional relation between the distance along the lane line between first vehicles in front of the road vehicles and the willingness degree lambda 5;
x1 and X2 characterize two fixed distance values on the distance axis along the lane line distance between the first vehicle in front of the pre-lane changing vehicle and the first vehicle in front of the pre-lane changing vehicle in the target lane.
In a preferred embodiment of the present invention, further comprising calculating the willingness factor λ 6 comprises,
calculating A ═ S1-S2+ V1 ═ t1+ D1;
a represents the distance which needs to be kept between the pre-lane changing vehicle and a first vehicle in front of a lane where the pre-lane changing vehicle is located when the pre-lane changing vehicle runs at a running speed V2;
v1 is the running speed of the pre-lane changing vehicle;
v2 is the running speed of the first vehicle in front of the lane where the lane-changing vehicle is located;
s1 is the braking distance from the braking of the pre-lane changing vehicle to the stopping;
s2 is the braking distance from the braking to the stopping of the first vehicle in front of the lane where the lane-changing vehicle is located;
t1the brake reaction time of the pre-lane-change vehicle;
d1 is the safe stopping distance between the pre-lane changing vehicle and the first vehicle in front of the lane where the pre-lane changing vehicle is located when the pre-lane changing vehicle and the first vehicle brake to stop;
when L1 > a + Δ 2, λ 6 ═ 0;
when L1 is less than or equal to A + delta 2, the willingness degree lambda 6 is calculated according to the formula six,
wherein, L1 is the initial distance between the pre-lane changing vehicle and the first vehicle in front of the lane where the pre-lane changing vehicle is located;
e, representing the ratio of the running speed of a first vehicle with a target lane positioned in front of the pre-lane-changing vehicle to the running speed of a first vehicle with the pre-lane-changing vehicle positioned in front of the lane;
e1 and E2 represent two fixed values on a running speed ratio axis of the ratio of the running speed of a first vehicle with a target lane positioned in front of a pre-lane changing vehicle to the running speed of the first vehicle with the lane positioned in front of the pre-lane changing vehicle;
k4representing the slope of a straight line of a functional relation between the ratio of the running speed of a first vehicle in front of a pre-lane-changing vehicle on a target lane and the running speed of the first vehicle in front of the lane in which the pre-lane-changing vehicle is located and the willingness degree lambda 6;
λ*and characterizing a fixed value which is greater than zero and less than or equal to 1 and is a variable capable of being calibrated.
The invention has the beneficial effects that:
the invention discloses a method for predicting the vehicle lane change to the rear of a vehicle in front of a target lane in automatic driving, which is characterized in that the driving state data of four vehicles, namely a pre-lane-change vehicle, a first vehicle in front of the pre-lane-change vehicle in the lane of the pre-lane-change vehicle, a first vehicle in front of the pre-lane-change vehicle in the target lane and a first vehicle in rear of the pre-lane-change vehicle in the target lane, are combined to calculate the willingness degree of the pre-lane-change vehicle to the rear of the vehicle in front of the target lane, whether the pre-lane-change vehicle can change to the rear of the vehicle in the target lane at the future moment is predicted according to the willingness degree, the factors of the peripheral vehicles interfering the decision; meanwhile, the data analysis calculation amount of a prediction module in the automatic driving system is effectively reduced, the operation difficulty and the operation cost of the automatic driving system are reduced, and the delay time of decision making is effectively improved.
Drawings
FIG. 1 is a flow chart of a prediction method in a preferred embodiment of the present invention;
FIG. 2 is a schematic view of a road condition illustrating how much the predicted vehicle will want to change to a lane ahead of the target lane in accordance with the preferred embodiment of the present invention;
FIG. 3a is a graph of v in a preferred embodiment of the inventionyA graph of the willingness degree lambda 2 is calculated when the value is 1;
FIG. 3b is a graph of v in a preferred embodiment of the inventionyA graph of the willingness degree lambda 2 is calculated when the value is 2;
FIG. 4 is a graph of the willingness factor λ 3 calculated in the preferred embodiment of the present invention;
FIG. 5a is a graph of the willingness factor λ 4 calculated in the preferred embodiment of the present invention;
FIG. 5b is a graph of the calculated desirability increment Δ λ in the preferred embodiment of the present invention;
FIG. 6 is a graph of the willingness factor λ 4 calculated in the preferred embodiment of the present invention;
fig. 7 is a graph of the calculation willingness degree λ 5 in the preferred embodiment of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
Examples
The present embodiment discloses a method for predicting a vehicle lane change to a position before a target lane in automatic driving, which, referring to fig. 1, comprises the following steps,
acquiring the following running state data of the vehicle in the current sampling period: the lane pre-changing vehicle 3, the first vehicle 8 in front of the lane where the lane pre-changing vehicle is located, the first vehicle 4 in front of the lane pre-changing vehicle in the target lane, and the first vehicle 0 in back of the lane pre-changing vehicle in the target lane. Referring to fig. 2, vehicle 3 represents a pre-lane-changing vehicle (hereinafter referred to as "vehicle 3"), vehicle 8 represents a first vehicle (hereinafter referred to as "vehicle 8") ahead of the lane in which the pre-lane-changing vehicle is located, vehicle 4 represents a first vehicle (hereinafter referred to as "vehicle 4") ahead of the pre-lane-changing vehicle in the target lane, and vehicle 0 represents a first vehicle (hereinafter referred to as "vehicle 0") behind the pre-lane-changing vehicle in the target lane. The traveling state data of each vehicle includes a traveling speed, a lateral speed, a distance between vehicles in a lane line direction (or "longitudinal distance"), an acceleration, a deceleration, a lateral acceleration/deceleration, and the like. When a vehicle is not present in fig. 2, the distance associated with the vehicle is considered to be infinite.
Calculating the willingness degree lambda of the vehicle 3 after changing the lane to the vehicle 4 by combining the acquired driving state data of each vehicle and the lane environment data, wherein lambda is more than or equal to 0 and less than or equal to 1;
when the willingness degree λ exceeds the willingness degree threshold, it is predicted that the vehicle 3 will make a lane change to a position after the vehicle 4 at a future time. Here, the willingness degree threshold is preset according to the driver characteristics, for example, the willingness degree threshold is set to 0.6, or 0.65, or 0.7, or the like.
Calculating the willingness λ includes excluding two sets of negative terms:
negative term 1: lateral velocity v of the vehicle 3 in the direction of the target laneyLess than or equal to zero, and for a certain time, the willingness degree of the vehicle 3 to change the lane to the lane where the vehicle 0 is located is zero. For example, the lateral velocity v of the vehicle 3 in the direction of the target laneyAnd when the time is less than or equal to zero and lasts for 2s, the willingness degree of the vehicle 3 to change the lane to the lane where the vehicle 0 is located is zero. The duration here is a calibrated quantity that can be adjusted. The following are to be mentioned: transverse velocity vyIf the value is larger than 0, the vehicle 3 is represented to be deviated to the target lane; transverse velocity vyLess than 0, indicating that the vehicle 3 is off the target lane.
Negative term 2: when the vehicle 4 is located behind the vehicle 8 and the traveling speed of the vehicle 4 is lower than the traveling speed of the vehicle 8, the willingness of the vehicle 3 to change the lane to the lane in which the vehicle 0 is located is zero.
When the driving state of each vehicle meets one of the two negative items or meets the two negative items simultaneously, the willingness degree of the vehicle 3 changing to the lane where the vehicle 4 is located and behind the vehicle 4 is 0, and when the negative items are met, subsequent calculation is not performed.
When the running state of each vehicle does not satisfy the above two sets of negative terms, the willingness degree λ is calculated by:
calculating the willingness degree lambda 1 under the influence of the traffic lane congestion degree;
the transverse speed v of the vehicle 3 in the direction of the lane of the vehicle 0 is satisfiedyCalculating the transverse speed v of the vehicle 3 towards the lane direction of the vehicle 0 under the condition that the transverse speed v is larger than or equal to zeroy Willingness degree lambda 2 under influence;
calculating a willingness degree lambda 3 under the influence of the longitudinal distance between the vehicle 3 and the vehicle 4;
calculating the willingness degree lambda 4 under the influence of the acceleration of the vehicle 3;
calculating a willingness degree lambda 5 under the influence of the longitudinal distance between the vehicle 8 and the vehicle 4;
calculating a willingness degree lambda 6 under the influence of the speed ratio of the vehicle 4 to the vehicle 8;
λ ═ max { λ 1, λ 2, λ 3, λ 4, λ 5, λ 6} (formula one);
the willingness λ to change lane of the vehicle 3 to the vehicle 4 and thereafter is calculated according to equation one.
In the technical solution of this embodiment, the willingness degrees λ 1, λ 2, λ 3, λ 4, λ 5, and λ 6 are preferably obtained by the following calculation:
(1) the above-mentioned willingness degree lambda 1 is calculated according to the formula one,
wherein ρ 1 represents the congestion degree in front of the lane where the vehicle 3 is located;
When the congestion degree is calculated, the congestion degree is represented by the number of vehicles within a certain distance, for example, 6 vehicles within 100m in front, and the calculated congestion degree is
(2) If the lateral velocity v of the vehicle 3 in the direction of the target lane isyGreater than zero, the willingness λ 2 for the vehicle 3 to change lane to and after the vehicle 4 and the lateral speed v of the vehicle 3 towards the target laneyAnd a lateral velocity vyThe duration of time is relevant. Here, the lateral velocity vyIf the value is larger than 0, the vehicle 3 is represented to be deviated to the target lane; transverse velocity vyLess than 0, indicating that the vehicle 3 is off the target lane. With reference to FIG. 3, at a transverse velocity vyThe time t for a certain value is the abscissa, the willingness degree lambda 2 is the ordinate to establish the coordinate system, the willingness degree lambda 2 and the transverse speed vyThe relationship as a function of the duration of a certain value is:
wherein t represents the transverse speed v of the pre-lane-changing vehicle towards the target lane directionyA time for which a certain fixed value lasts;
t1 and t2 respectively represent two fixed time values on the axis of abscissa, for example, t1 takes 1s and t2 takes 2 s. Here, t1 and t2 are both adjustable calibration amounts.
Referring to FIG. 3(a), the lateral velocity vyFunctional relationship when equal to 1. Referring to FIG. 3(b), the lateral velocity vyFunctional relationship when equal to 2.
The horizontal coordinate value, vertical coordinate value and slope of the break point of the straight line shown in FIG. 3 are all calibrated parameters capable of being adjusted, and are related to the horizontal velocity vyIs related to the magnitude of the transverse velocity vyThe larger the value of ordinate is, the smaller the value of abscissa in fig. 3 is, the larger the slope of the straight line is, but the maximum value of will degree λ 2 is 1.
(3) The calculation will degree a 3 includes,
calculating L1 ═ a + B, A ═ S1-S2+ V1 × t1+ D1;
a represents the distance which needs to be kept from the vehicle 8 when the vehicle 3 runs at a running speed V2;
b characterises the vehicle 3 at a deceleration axA travel distance decelerated from the travel speed V1 to the travel speed V2;
l1 is the initial spacing between vehicle 3 and vehicle 8;
v1 is the running speed of the vehicle 3;
v2 is the running speed of the vehicle 8;
s1 is the braking distance from the braking of the vehicle 3 to the stop;
s2 is the braking distance from the braking of the vehicle 8 to the stop;
t1is the brake reaction time of the vehicle 3;
d1 is the safe stopping distance between vehicle 3 and vehicle 8 when both are braking to a stop;
when B is equal to (L1-A) less than or equal to 0, the willingness degree lambda 3 is equal to 1;
when B ═ 0 (L1-a) > and V1 ≦ V2, the desirability λ 3 is 0;
when B ═ L1-a) > 0, and V1 > V2, the deceleration a of the vehicle 3 is calculated according to equation twox：
Presetting the deceleration a of the comfort braking according to the driver characteristicsThresReferring to FIG. 4, at a deceleration aThresAnd deceleration axThe difference value of (A) is an abscissa, the willingness degree lambda 3 is an ordinate to establish a coordinate system, the willingness degree lambda 3 and the deceleration aThresAnd deceleration axThe functional relationship between the difference values of (a) and (b) is:
wherein a represents a preset comfort braking deceleration a of the pre-track-changing vehicleThresAnd deceleration axA difference of (d);
k1characterizing deceleration aThresAnd deceleration axThe slope of a straight line of the functional relationship between the difference value of (a) and the willingness degree lambda 3;
a1characterised by a fixed value of deceleration on the axis of abscissa, e.g. a10.5g was taken. Which is an adjustable calibration quantity.
(4) When L1 > (V1-V2) × Δ T, λ 4 ═ 0;
if L1 ≦ (V1-V2) × Δ T otherwise, the following calculation is performed:
firstly, a will degree is calculated according to the current actual acceleration A of the vehicle 3, then an increment delta lambda of the will degree is calculated according to the duration time of the acceleration A, the increment of the will degree changes along with the increase of the duration time, the slope of an increment curve corresponding to different accelerations A is different, the larger the value of the acceleration A is, the larger the slope of the increment curve is, the more the will degree lambda 4 is the sum of the will degree corresponding to the actual acceleration A and the increment of the will degree, but the sum of the two needs to be smaller than 1.
A coordinate system is established by taking the current actual acceleration A of the vehicle 3 as an abscissa and the willingness degree lambda 4 as an ordinate, and the functional relationship between the willingness degree lambda 4 and the current actual acceleration A of the vehicle 3 is shown in FIG. 5(a),
a represents the actual acceleration of the vehicle 3;
k2the slope of a straight line representing the functional relationship between the actual acceleration of the vehicle 3 and the willingness degree lambda 4;
A1characterised by a fixed acceleration value on the axis of abscissa, e.g. A10.1g was taken. Where A is1To be able to adjust the amount of calibration.
The delta lambda represents the willingness degree increment of the pre-lane-changing vehicle when the actual acceleration exceeds the acceleration threshold value for a certain time;
Δ T is a calibratable amount;
v1 is the running speed of the pre-lane changing vehicle;
v2 is the running speed of the first vehicle in front of the lane where the lane-changing vehicle is located;
l1 is the initial spacing between vehicle 3 and vehicle 8.
Referring to fig. 5(b), a coordinate system is established with the abscissa as the time during which the actual acceleration of the vehicle 3 exceeds the acceleration threshold value, and the ordinate as the willingness degree increment Δ λ, and the functional relationship between the time during which the actual acceleration of the vehicle 3 exceeds the acceleration threshold value and the willingness degree increment Δ λ is shown in fig. 5 (b).
In fig. 5(a) and 5(b), the maximum value of the ordinate is 1, and the abscissa value, the ordinate value, and the slope of the straight line of the break point are adjustable calibration parameters.
(5) The calculation of the above-mentioned willingness degree a 5 includes,
calculating A ═ S1-S2+ V1 ═ t1+ D1;
a represents the distance which needs to be kept from the vehicle 8 when the vehicle 3 runs at a running speed V2;
v1 is the running speed of the vehicle 3;
v2 is the running speed of the vehicle 8;
s1 is the braking distance from the braking of the vehicle 3 to the stop;
s2 is the braking distance from the braking of the vehicle 8 to the stop;
t1is the brake reaction time of the vehicle 3;
d1 is the safe stopping distance between vehicle 3 and vehicle 8 when both are braking to a stop;
l1 is the initial spacing between vehicle 3 and vehicle 8;
when L1 > a + Δ 1, λ 5 ═ 0; here, Δ 1 represents a fixed distance value, which is an adjustable calibration quantity.
When L1 is less than or equal to a + Δ 1, the desirability λ 5 is related to the distance between the vehicle 8 and the vehicle 4 along the lane line, a coordinate system is established with the distance between the vehicle 8 and the vehicle 4 along the lane line as an abscissa and the desirability λ 5 as an ordinate, the functional relationship between the desirability λ 5 and the distance between the vehicle 8 and the vehicle 4 along the lane line is shown in fig. 6,
wherein X represents the along-lane distance between the vehicle 8 and the vehicle 4;
k3a slope of a straight line representing a functional relationship between a distance along a lane line between the vehicle 8 and the vehicle 4 and the willingness factor lambda 5;
two fixed distance values on the X1 and X2 abscissa axes, for example, X1 is 2m, and X2 is 0.5s × V1; both X1 and X2 are standard quantities that can be adjusted.
In fig. 6, the maximum value of the ordinate of the vertical axis is 1, and the abscissa value, the ordinate value, and the slope of the straight line of the break point are all adjustable calibration parameters.
(6) Calculating the willingness degree λ 6 includes:
calculating A ═ S1-S2+ V1 ═ t1+ D1;
a represents the distance which needs to be kept from the vehicle 8 when the vehicle 3 runs at a running speed V2;
v1 is the running speed of the vehicle 3;
v2 is the running speed of the vehicle 8;
v3 is the running speed of the vehicle 4;
s1 is the braking distance from the braking of the vehicle 3 to the stop;
s2 is the braking distance from the braking of the vehicle 8 to the stop;
t1is the brake reaction time of the vehicle 3;
d1 is the safe stopping distance between vehicle 3 and vehicle 8 when both are braking to a stop;
l1 is the initial spacing between vehicle 3 and vehicle 8;
when L1 > a + Δ 2, λ 6 ═ 0. Here, Δ 2 represents a fixed distance value, which is an adjustable calibration quantity
When L1 is equal to or less than a + Δ 2, the will degree λ 6 is related to the traveling speed ratio E of the vehicle 4 and the vehicle 8, a coordinate system is established with the traveling speed ratio of the vehicle 4 and the vehicle 8 as an abscissa and the will degree λ 6 as an ordinate, and referring to fig. 7, the function relationship between the will degree λ 6 and the traveling speed ratio E of the vehicle 4 and the vehicle 8 is:
wherein E represents the travel speed ratio of the vehicle 4 to the vehicle 8;
e1 and E2 characterize two fixed values on the abscissa, e.g., 1 for E1 and 1.5 for E2. Here, both E1 and E2 are adjustable calibration amounts.
k4The slope of a straight line representing the functional relationship between the ratio of the running speed of the vehicle 4 to the running speed of the vehicle 8 and the willingness degree lambda 6;
λ*the characterization is a fixed value which is greater than zero and less than or equal to 1 and is an adjustable calibration quantity.
In fig. 7, the horizontal coordinate value, the vertical coordinate value, and the slope of the straight line of the break point are adjustable calibration parameters, except that the maximum value of the vertical coordinate is 1.
In the method for predicting the vehicle lane change to the rear of the vehicle in the target lane in the automatic driving process, the willingness degree of the pre-lane-change vehicle to the rear of the vehicle in the target lane is calculated by combining the driving state data of the pre-lane-change vehicle, the first vehicle in the lane where the pre-lane-change vehicle is located, the first vehicle in the target lane in front of the pre-lane-change vehicle and the first vehicle in the target lane in rear of the pre-lane-change vehicle, and the willingness degree is used for predicting whether the pre-lane-change vehicle can change to the rear of the vehicle in the target lane at the future time, so that the factor that the surrounding vehicles interfere the decision of the vehicle is effectively eliminated, and the decision reliability of the vehicle is improved; meanwhile, the data analysis calculation amount of a prediction module in the automatic driving system is effectively reduced, the operation difficulty and the operation cost of the automatic driving system are reduced, and the delay time of decision making is effectively improved.
The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (8)
1. A method of predicting a vehicle after a lane change to a target lane ahead in an autonomous driving, characterized by: comprises the following steps of (a) carrying out,
acquiring the following running state data of the vehicle in the current sampling period: the lane pre-changing system comprises a pre-lane changing vehicle, a first vehicle in front of a lane where the pre-lane changing vehicle is located, a first vehicle in front of the pre-lane changing vehicle in a target lane, and a first vehicle behind the pre-lane changing vehicle in the target lane;
calculating the willingness degree lambda of the pre-lane-changing vehicle after changing the lane to the vehicle in front of the target lane by combining the acquired driving state data of each vehicle and the lane environment data, wherein lambda is more than or equal to 0 and less than or equal to 1;
when the willingness degree exceeds a willingness degree threshold value, predicting that the pre-lane-changing vehicle will change lanes to be behind a front vehicle of the target lane at a future moment;
calculating the willingness factor lambda also includes,
calculating the willingness degree lambda 1 under the influence of the traffic lane congestion degree;
the transverse speed of the pre-lane-changing vehicle towards the target lane direction is higher thanCalculating the lateral speed v of the pre-lane-changing vehicle towards the target lane under the condition of being equal to zeroyWillingness degree lambda 2 under influence;
calculating the willingness degree lambda 3 under the influence of the longitudinal distance between the pre-lane changing vehicle and a first vehicle in front of the lane where the pre-lane changing vehicle is located;
calculating the willingness degree lambda 4 under the influence of the acceleration of the pre-lane-changing vehicle;
calculating the willingness degree lambda 5 under the influence of the longitudinal distance between a first vehicle in front of the lane where the pre-lane-changing vehicle is located and a first vehicle in front of the pre-lane-changing vehicle in a target lane;
calculating the willingness degree lambda 6 under the influence of the speed ratio of a first vehicle of a target lane in front of a pre-lane-changing vehicle to a first vehicle in front of a lane in which the pre-lane-changing vehicle is located;
λ ═ max { λ 1, λ 2, λ 3, λ 4, λ 5, λ 6} (formula one);
and calculating the willingness degree lambda of the pre-lane-changing vehicle after changing the lane to the front of the target lane according to the formula I.
2. The method of predicting vehicle lane change to after the vehicle ahead of the target lane in autonomous driving of claim 1, wherein: the calculation of the willingness degree lambda includes,
when the transverse speed of the pre-lane-changing vehicle towards the target lane direction is less than zero and is maintained for a certain time, the willingness degree of the pre-lane-changing vehicle to change the lane to the target lane is zero;
or when the running speed of the first vehicle in front of the pre-lane-changing vehicle in the target lane is lower than the running speed of the first vehicle in front of the lane in which the pre-lane-changing vehicle is located and the first vehicle in front of the pre-lane-changing vehicle in the target lane is located behind the first vehicle in front of the lane in which the pre-lane-changing vehicle is located, the willingness degree of the pre-lane-changing vehicle to change to the target lane is zero.
3. The method of predicting vehicle lane change to after the vehicle ahead of the target lane in autonomous driving of claim 1, wherein: the willingness degree lambda 1 is calculated according to the formula one,
the rho 1 represents the congestion degree in front of the lane where the pre-lane-changing vehicle is located;
ρ 2 represents the degree of congestion ahead of the first vehicle behind the pre-lane-change vehicle in the target lane.
4. The method of predicting vehicle lane change to after the vehicle ahead of the target lane in autonomous driving of claim 1, wherein: the willingness degree lambda 2 is calculated according to the formula two,
wherein t represents the transverse speed v of the pre-lane-changing vehicle towards the target lane directionyA time for which a certain fixed value lasts;
t1 and t2 respectively represent two fixed time values on the time axis of t.
5. The method of predicting vehicle lane change to after the vehicle ahead of the target lane in autonomous driving of claim 1, wherein: the calculation of said willingness degree 3 includes,
calculating L1 ═ a + B, A ═ S1-S2+ V1 × t1+D1；
A represents the distance which needs to be kept between the pre-lane changing vehicle and a first vehicle in front of a lane where the pre-lane changing vehicle is located when the pre-lane changing vehicle runs at a running speed V2;
b characterizes the pre-lane change vehicle at deceleration axA travel distance decelerated from the travel speed V1 to the travel speed V2;
l1 is the initial distance between the pre-lane changing vehicle and the first vehicle in front of the lane where the pre-lane changing vehicle is located;
v1 is the running speed of the pre-lane changing vehicle;
v2 is the running speed of the first vehicle in front of the lane where the lane-changing vehicle is located;
s1 is the braking distance from the braking of the pre-lane changing vehicle to the stopping;
s2 is the braking distance from the braking to the stopping of the first vehicle in front of the lane where the lane-changing vehicle is located;
t1the brake reaction time of the pre-lane-change vehicle;
d1 is the safe stopping distance between the pre-lane changing vehicle and the first vehicle in front of the lane where the pre-lane changing vehicle is located when the pre-lane changing vehicle and the first vehicle brake to stop;
when B is equal to (L1-A) less than or equal to 0, the willingness degree lambda 3 is equal to 1;
when B ═ 0 (L1-a) > and V1 ≦ V2, the desirability λ 3 is 0;
when B ═ L1-a) > 0, and V1 > V2, deceleration a of the pre-track vehicle is calculated according to equation twox：
Calculating the willingness degree lambda 3 according to a formula three:
wherein a represents a preset comfort braking deceleration a of the pre-track-changing vehicleThresAnd deceleration axA difference of (d);
k1characterizing deceleration aThresAnd deceleration axThe slope of a straight line of the functional relationship between the difference value of (a) and the willingness degree lambda 3;
a1characterizing deceleration aThresAnd deceleration axA fixed deceleration value on the deceleration axis.
6. The method of predicting vehicle lane change to after the vehicle ahead of the target lane in autonomous driving of claim 1, wherein: the willingness degree lambda 4 is calculated according to the formula four,
a represents the actual acceleration of the pre-lane-changing vehicle;
k2representing the slope of a straight line of a functional relation between the actual acceleration of the pre-lane-changing vehicle and the willingness degree lambda 4;
A1representing a fixed acceleration value of an acceleration axis of the actual acceleration of the pre-lane-changing vehicle;
Δ λ represents the willingness increment of the pre-lane-change vehicle for a certain time period when the actual acceleration exceeds the acceleration threshold.
7. The method of predicting vehicle lane change to after the vehicle ahead of the target lane in autonomous driving of claim 1, wherein: the calculation of said willingness degree a 5 includes,
calculating A ═ S1-S2+ V1 ═ t1+D1；
A represents the distance which needs to be kept between the pre-lane changing vehicle and a first vehicle in front of a lane where the pre-lane changing vehicle is located when the pre-lane changing vehicle runs at a running speed V2;
v1 is the running speed of the pre-lane changing vehicle;
v2 is the running speed of the first vehicle in front of the lane where the lane-changing vehicle is located;
s1 is the braking distance from the braking of the pre-lane changing vehicle to the stopping;
s2 is the braking distance from the braking to the stopping of the first vehicle in front of the lane where the lane-changing vehicle is located;
t1the brake reaction time of the pre-lane-change vehicle;
d1 is the safe stopping distance between the pre-lane changing vehicle and the first vehicle in front of the lane where the pre-lane changing vehicle is located when the pre-lane changing vehicle and the first vehicle brake to stop;
when L1 > a + Δ 1, λ 5 ═ 0;
when L1 is less than or equal to A + delta 1, calculating the willingness degree lambda 5 according to the formula five,
wherein, L1 is the initial distance between the pre-lane changing vehicle and the first vehicle in front of the lane where the pre-lane changing vehicle is located;
Δ 1 represents a fixed distance value;
x represents the distance along the lane line between a first vehicle in front of the lane where the pre-lane-changing vehicle is located and a first vehicle in front of the pre-lane-changing vehicle in the target lane;
k3representing the slope of a straight line of a functional relation between the distance along the lane line between a first vehicle in front of the lane where the pre-lane-changing vehicle is located and a first vehicle in front of the pre-lane-changing vehicle in a target lane and the willingness degree lambda 5;
x1 and X2 characterize two fixed distance values on the distance axis along the lane line distance between the first vehicle in front of the pre-lane changing vehicle and the first vehicle in front of the pre-lane changing vehicle in the target lane.
8. The method of predicting vehicle lane change to after the vehicle ahead of the target lane in autonomous driving of claim 1, wherein: the calculation of said willingness degree a 6 includes,
calculating A ═ S1-S2+ V1 ═ t1+D1；
A represents the distance which needs to be kept between the pre-lane changing vehicle and a first vehicle in front of a lane where the pre-lane changing vehicle is located when the pre-lane changing vehicle runs at a running speed V2;
v1 is the running speed of the pre-lane changing vehicle;
v2 is the running speed of the first vehicle in front of the lane where the lane-changing vehicle is located;
s1 is the braking distance from the braking of the pre-lane changing vehicle to the stopping;
s2 is the braking distance from the braking to the stopping of the first vehicle in front of the lane where the lane-changing vehicle is located;
t1the brake reaction time of the pre-lane-change vehicle;
d1 is the safe stopping distance between the pre-lane changing vehicle and the first vehicle in front of the lane where the pre-lane changing vehicle is located when the pre-lane changing vehicle and the first vehicle brake to stop;
when L1 > a + Δ 2, λ 6 ═ 0;
when L1 is less than or equal to A + delta 2, the willingness degree lambda 6 is calculated according to the formula six,
wherein, L1 is the initial distance between the pre-lane changing vehicle and the first vehicle in front of the lane where the pre-lane changing vehicle is located;
Δ 2 represents a fixed distance value;
e, representing the ratio of the running speed of a first vehicle with a target lane positioned in front of the pre-lane-changing vehicle to the running speed of a first vehicle with the pre-lane-changing vehicle positioned in front of the lane;
e1 and E2 represent two fixed values on a running speed ratio axis of the ratio of the running speed of a first vehicle with a target lane positioned in front of a pre-lane changing vehicle to the running speed of the first vehicle with the lane positioned in front of the pre-lane changing vehicle;
k4representing the slope of a straight line of a functional relation between the ratio of the running speed of a first vehicle in front of a pre-lane-changing vehicle on a target lane and the running speed of the first vehicle in front of the lane in which the pre-lane-changing vehicle is located and the willingness degree lambda 6;
λ*a fixed value greater than zero and less than or equal to 1 is characterized.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911242729.9A CN110920623B (en) | 2019-12-06 | 2019-12-06 | Prediction method for vehicle changing to front of target lane and vehicle behind target lane in automatic driving |
| PCT/CN2019/123927 WO2021109164A1 (en) | 2019-12-06 | 2019-12-09 | Prediction method for lane changing of vehicle to behind vehicle ahead in target lane in automatic driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911242729.9A CN110920623B (en) | 2019-12-06 | 2019-12-06 | Prediction method for vehicle changing to front of target lane and vehicle behind target lane in automatic driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110920623A CN110920623A (en) | 2020-03-27 |
| CN110920623B true CN110920623B (en) | 2021-02-02 |
Family
ID=69857378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911242729.9A Active CN110920623B (en) | 2019-12-06 | 2019-12-06 | Prediction method for vehicle changing to front of target lane and vehicle behind target lane in automatic driving |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110920623B (en) |
| WO (1) | WO2021109164A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7439910B2 (en) * | 2020-04-06 | 2024-02-28 | 日産自動車株式会社 | Vehicle behavior estimation method, vehicle control method, and vehicle behavior estimation device |
| WO2023168630A1 (en) * | 2022-03-09 | 2023-09-14 | 华为技术有限公司 | Vehicle control method and related apparatus |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4507886B2 (en) * | 2005-01-14 | 2010-07-21 | 株式会社デンソー | Vehicle travel control device |
| KR101478135B1 (en) * | 2013-12-02 | 2014-12-31 | 현대모비스(주) | Augmented reality lane change helper system using projection unit |
| US20200001867A1 (en) * | 2017-03-01 | 2020-01-02 | Honda Motor Co., Ltd. | Vehicle control apparatus, vehicle control method, and program |
| JP6494121B2 (en) * | 2017-03-01 | 2019-04-03 | 本田技研工業株式会社 | Lane change estimation device, lane change estimation method, and program |
| CN107644551A (en) * | 2017-09-04 | 2018-01-30 | 维沃移动通信有限公司 | One kind is overtaken other vehicles pre-judging method and terminal |
| US10611371B2 (en) * | 2017-09-14 | 2020-04-07 | Toyota Motor Engineering & Manufacturing North America, Inc. | System and method for vehicle lane change prediction using structural recurrent neural networks |
| JP7151179B2 (en) * | 2018-05-31 | 2022-10-12 | マツダ株式会社 | Lane change estimation device and lane change estimation method, vehicle control device and vehicle control method |
-
2019
- 2019-12-06 CN CN201911242729.9A patent/CN110920623B/en active Active
- 2019-12-09 WO PCT/CN2019/123927 patent/WO2021109164A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| CN110920623A (en) | 2020-03-27 |
| WO2021109164A1 (en) | 2021-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109669461B (en) | Decision-making system for automatically driving vehicle under complex working condition and track planning method thereof | |
| CN109649393B (en) | Path planning method and device for automatically driving lane change | |
| US10838423B2 (en) | Intelligent vehicle navigation systems, methods, and control logic for deriving road segment speed limits | |
| DE102015114465B4 (en) | Method for path planning for an evasive steering maneuver | |
| CN108919795A (en) | A kind of autonomous driving vehicle lane-change decision-making technique and device | |
| US6873911B2 (en) | Method and system for vehicle operator assistance improvement | |
| CN108032858B (en) | Adaptive cruise control method and system based on bypass driving path prediction | |
| CN113291308B (en) | Vehicle self-learning lane-changing decision-making system and method considering driving behavior characteristics | |
| US8078373B2 (en) | Vehicle dynamics prediction with lane/path information using a preview-correction-prediction approach | |
| JP2002137652A (en) | Precedent vehicle follow-up controlling device | |
| EP3741638A1 (en) | Vehicle control device | |
| CN111547051A (en) | Control system and control method for determining trajectory of motor vehicle based on interaction duration | |
| CN112061106B (en) | Automatic driving control method, device, vehicle and storage medium | |
| US11708069B2 (en) | Obstacle avoidance apparatus and obstacle avoidance route generating apparatus | |
| CN110920623B (en) | Prediction method for vehicle changing to front of target lane and vehicle behind target lane in automatic driving | |
| EP3738849A1 (en) | Vehicle control device | |
| CN111145552A (en) | Planning method for vehicle dynamic lane changing track based on 5G network | |
| CN113428141A (en) | Intelligent detection method and system for timely response of emergency cut-in of front vehicle | |
| JP4899626B2 (en) | Travel control device | |
| CN110920622B (en) | Prediction method before vehicle changes lane to target lane in automatic driving | |
| CN112224202B (en) | Multi-vehicle cooperative collision avoidance system and method under emergency working condition | |
| CN113269974A (en) | Target loss early warning and control method and device | |
| CN112542061A (en) | Lane borrowing and overtaking control method, device and system based on Internet of vehicles and storage medium | |
| CN115662131B (en) | Multi-lane collaborative lane changing method for road accident section in network environment | |
| JP4720166B2 (en) | Vehicle speed detection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |