WO2023201964A1 - 一种跟车目标确定方法、装置、设备及介质 - Google Patents

一种跟车目标确定方法、装置、设备及介质 Download PDF

Info

Publication number
WO2023201964A1
WO2023201964A1 PCT/CN2022/117116 CN2022117116W WO2023201964A1 WO 2023201964 A1 WO2023201964 A1 WO 2023201964A1 CN 2022117116 W CN2022117116 W CN 2022117116W WO 2023201964 A1 WO2023201964 A1 WO 2023201964A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
followed
lane line
distance
parameter
Prior art date
Application number
PCT/CN2022/117116
Other languages
English (en)
French (fr)
Inventor
罗凤梅
李超群
陈远龙
李勇
隋记魁
李世豪
李林丰
陈超
杜江涛
李瑞龙
Original Assignee
合众新能源汽车股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 合众新能源汽车股份有限公司 filed Critical 合众新能源汽车股份有限公司
Publication of WO2023201964A1 publication Critical patent/WO2023201964A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/14—Adaptive cruise control
    • B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
    • B60W30/165—Automatically following the path of a preceding lead vehicle, e.g. "electronic tow-bar"
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/53—Road markings, e.g. lane marker or crosswalk
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/802—Longitudinal distance

Definitions

  • This application relates to the field of automobile automation technology, and specifically to a method, device, equipment and medium for determining a car following target.
  • This function ensures that the driver can drive without hands and feet within a certain period of time.
  • This function mainly obtains the lane lines of the road section where the vehicle is located through the image acquisition device to plan the vehicle's driving trajectory to ensure that the vehicle drives within the lane.
  • the above control method mainly relies on the lane image captured by the image acquisition device. When affected by weather or the lane is congested, the lane image will be unclear, and when the confidence level is low, the autonomous driving mode will be exited.
  • the car-following mode is usually enabled to select a motor vehicle in front of the vehicle that meets the lateral distance from the vehicle to follow the trajectory of the motor vehicle and drive automatically.
  • the confidence of the lane image is low, it is impossible to determine whether the following target is in the same lane as the own vehicle based on the lateral distance alone, causing safety risks.
  • Embodiments of the present application provide a vehicle following target determination method, device, equipment and medium for determining whether the vehicle following target is in the same lane as the own vehicle.
  • embodiments of the present application provide a method for determining a car following target.
  • the method includes:
  • the vehicle following instruction obtain the lane line information fed back by the own vehicle's sensor and the first vehicle parameters; wherein the lane line information at least includes the feedback value of the parameter item characterizing the lane line trajectory; the first vehicle parameter at least includes the own vehicle parameter.
  • the vehicle to be followed is the vehicle located in front of the vehicle selected by the sensor based on preset decision conditions;
  • Whether to use the vehicle to be followed as a following target is determined based on the lane line area and the location of the vehicle to be followed.
  • the embodiment of the present application determines the feedback value of the parameter item by obtaining the lane line information fed back by the own vehicle's sensor, and determines the predicted value of the parameter item based on the first vehicle parameter. Since the first vehicle parameters include the current vehicle speed, curvature, and longitudinal distance from the vehicle to be followed, the above predicted value represents the lane line area predicted based on the driving status of the vehicle to be followed and the vehicle. In addition, since the above feedback value represents the lane line area of the road section where the vehicle is located detected by the vehicle's sensor, the final lane line area can be comprehensively estimated based on the feedback value and the predicted value, and then by detecting whether the vehicle to be followed is in the lane based on its location. within the line area to determine whether to use the vehicle to be followed as the following target.
  • the vehicle following instruction obtain the lane line information fed back by the own vehicle's sensor and the first vehicle parameters; wherein the lane line information at least includes the feedback value of the parameter item characterizing the lane line trajectory; the first vehicle parameter at least includes the own vehicle parameter.
  • the vehicle to be followed is the vehicle located in front of the vehicle selected by the sensor based on preset decision conditions;
  • Whether to use the vehicle to be followed as a following target is determined based on the lane line area and the location of the vehicle to be followed.
  • the parameter terms include constant term coefficients, linear term coefficients, quadratic term coefficients and cubic term coefficients; determining the predicted value of the parameter term based on the first vehicle parameter includes:
  • the preset cubic term calibration value is used as the predicted value of the cubic term coefficient, and the initial value of the coefficient to be processed is determined according to the first vehicle parameter; wherein the coefficient to be processed includes the constant term coefficient, the The linear term coefficient and the quadratic term coefficient;
  • the second vehicle parameter of the vehicle is sampled every first preset time period; wherein the second vehicle parameter is determined based on the sensor of the vehicle, and the second vehicle parameter includes the vehicle's own Vehicle speed and yaw rate;
  • the prediction data is determined according to the second vehicle parameters; wherein the prediction data at least includes a longitudinal correction distance, a correction angle and a lateral correction distance; the longitudinal correction distance represents the current driving direction of the vehicle, and the speed of the vehicle is used to drive
  • the first preset time length corresponds to the longitudinal distance difference between the front and rear body of the vehicle;
  • the correction angle represents the angle change of the front and rear body of the vehicle in the current driving direction, and the first preset time period corresponds to the vehicle speed;
  • the lateral correction distance represents the current driving direction of the vehicle, and the lateral distance difference between the front and rear vehicle bodies corresponding to the first preset duration of driving at the vehicle speed;
  • the prediction value is determined based on the prediction data and the initial value of the coefficient to be processed.
  • the vehicle speed and yaw angular velocity of the vehicle are collected at preset intervals, and each parameter in the lane line trajectory equation is determined based on the vehicle speed and yaw angular velocity after each collection.
  • the predicted value of the item is used to improve the prediction accuracy of the lane line trajectory area.
  • determining the initial value of the coefficient to be processed according to the first vehicle parameter includes:
  • the estimated time is determined based on the longitudinal distance and the vehicle speed of the own vehicle, and the initial value of the quadratic term coefficient is determined based on the curvature of the own vehicle and the estimated time; wherein, the estimated time is represented by the vehicle's curvature Vehicle speed, the time it takes for the vehicle to reach the location of the vehicle to be followed from its current location.
  • the embodiment of the present application presets the initial values of the constant term and the initial value of the linear term corresponding to different speed intervals.
  • the constant term coefficient represents the lateral distance between the lane line trajectory and the vehicle
  • the linear term coefficient represents The heading angle of the lane line trajectory
  • these two parameter items are negatively related to the vehicle speed, so the initial value of the constant term coefficient and the initial value of the linear term coefficient can be determined according to the preset speed interval where the vehicle speed is located.
  • the quadratic term coefficient represents the curvature of the lane line trajectory
  • the estimated time from the current position of the vehicle to the location of the vehicle to be followed can be obtained based on the longitudinal distance and the vehicle's speed. According to the estimated time and the vehicle's speed, the estimated time is The curvature determines the initial value of the cubic term coefficient.
  • determining prediction data according to the second vehicle parameter includes:
  • a lateral correction distance corresponding to the second vehicle parameter is determined based on the correction angle and the first preset time distance.
  • the longitudinal correction distance, correction angle and lateral correction distance of a single sampling are determined based on the second vehicle parameters obtained from each sampling.
  • the longitudinal correction distance represents the longitudinal distance change of the car body before and after the vehicle reaches the position of the vehicle to be followed when traveling at the speed of the own vehicle.
  • the correction angle represents the change of the longitudinal distance of the vehicle body before and after the vehicle reaches the position of the vehicle to be followed from the current position when traveling at the speed of the own vehicle.
  • the change in body angle and the lateral correction distance represent the change in the lateral distance of the body before and after the vehicle reaches the position of the vehicle to be followed from the current position to the position of the vehicle to be followed while traveling at the speed of the vehicle.
  • determining the predicted value based on the predicted data and the initial value of the coefficient to be processed includes:
  • the longitudinal correction distance corresponding to the second vehicle parameter obtained based on each sampling is accumulated to obtain the longitudinal correction value; the correction angle corresponding to the second vehicle parameter obtained based on each sampling is accumulated to obtain the angle correction value; the angle correction value is obtained based on each sampling.
  • the lateral correction distance corresponding to the sampled second vehicle parameter is accumulated to obtain a lateral accumulation value;
  • the initial value of the quadratic term coefficient is used as the predicted value of the quadratic term coefficient.
  • the correction parameters obtained from each sampling are accumulated.
  • the correction parameters are brought into the equation to obtain the predicted value of the constant term coefficient and the predicted value of the linear term coefficient.
  • the quadratic term is determined When the initial value of the quadratic term coefficient is substituted, the longitudinal distance between the vehicle and the vehicle to be followed is substituted, that is, the real road conditions of the vehicle are referenced. Therefore, the initial value of the quadratic term coefficient can be used as the predicted value of the quadratic term coefficient.
  • the lane line information also includes a confidence indicating whether the sensor feedback lane line trajectory is accurate; the lane line area of the road section where the vehicle is located is determined based on the feedback value and the predicted value.
  • the least squares method is used to perform a fitting operation on the feedback value and the predicted value, and the lane line area is determined according to the fitting operation result of the parameter item.
  • the parameter items fed back by the sensor are selected to determine the lane line area; when the confidence level is low, the predicted values of the parameter items are used to determine the lane line area. And when the confidence level is moderate, the feedback values and predicted values of the parameter items are fitted by the least squares method to obtain the comprehensive sensor feedback results and the final lane line area based on the vehicle parameter prediction results, thus improving the lane line trajectory. prediction accuracy.
  • determining whether to use the vehicle to be followed as a following target based on the lane line area and the location of the vehicle to be followed includes:
  • the driving information at least includes the speed, acceleration, heading angle and location of the vehicle to be followed;
  • the embodiment of the present application determines the trajectory of the vehicle to be followed based on the current driving information of the vehicle to be followed, thereby determining whether the vehicle to be followed leaves the lane line area.
  • the vehicle to be followed is about to leave the lane line area, it means that the vehicle to be followed and the vehicle are not in the same lane line. At this time, the vehicle to be followed should not be used as the following target.
  • determining whether to use the vehicle to be followed as a following target based on the left and right boundaries of the vehicle body and the lane line area includes:
  • the vehicle to be followed is used as the following target; wherein the first distance represents the lateral distance from the center point of the vehicle to the left boundary of the vehicle body; The second distance represents the lateral distance from the center point of the vehicle to the left boundary of the lane line area;
  • the vehicle to be followed is used as the following target; where the third distance represents the lateral direction from the center point of the vehicle to the right boundary of the vehicle body. distance; the fourth distance represents the lateral distance from the center point of the vehicle to the right boundary of the lane line area;
  • the vehicle to be followed is used as the following target
  • the vehicle to be followed is used as the following target; wherein the first weight and the second weight are based on The confidence level is determined, and the first weight is greater than the second weight.
  • the embodiment of this application sets corresponding weights according to different confidence levels. Therefore, it can be determined whether the vehicle to be followed should leave the lane line area based on the comparison results of the lateral distance between the vehicle and the left and right boundaries of the lane line and the lateral distance between the vehicle and the left and right boundaries of the vehicle to be followed, thereby avoiding the selected The vehicle following target is not in the same lane as the vehicle.
  • a vehicle following target determination device which includes:
  • the parameter acquisition module is configured to acquire the lane line information and the first vehicle parameter fed back by the vehicle sensor in response to the vehicle following instruction; wherein the lane line information at least includes a feedback value of a parameter item characterizing the lane line trajectory; the The first vehicle parameters at least include the own vehicle speed of the own vehicle, the curvature of the own vehicle, and the longitudinal distance between the vehicle to be followed and the own vehicle.
  • the vehicle to be followed is located in front of the vehicle selected by the sensor based on preset decision conditions. vehicle;
  • an area prediction module configured to determine the predicted value of the parameter item based on the first vehicle parameter, and determine the lane line area of the road segment where the vehicle is located based on the feedback value and the predicted value;
  • a target determination module is configured to determine whether to use the vehicle to be followed as a following target based on the lane line area and the location of the vehicle to be followed.
  • the parameter term includes a constant term coefficient, a linear term coefficient, a quadratic term coefficient and a cubic term coefficient; performing the step of determining the predicted value of the parameter term based on the first vehicle parameter, so
  • the above area prediction module is configured as:
  • the preset cubic term calibration value is used as the predicted value of the cubic term coefficient, and the initial value of the coefficient to be processed is determined according to the first vehicle parameter; wherein the coefficient to be processed includes the constant term coefficient, the The linear term coefficient and the quadratic term coefficient;
  • the second vehicle parameter of the vehicle is sampled every first preset time period; wherein the second vehicle parameter is determined based on the sensor of the vehicle, and the second vehicle parameter includes the vehicle's own Vehicle speed and yaw rate;
  • the prediction data is determined according to the second vehicle parameters; wherein the prediction data at least includes a longitudinal correction distance, a correction angle and a lateral correction distance; the longitudinal correction distance represents the current driving direction of the vehicle, and the speed of the vehicle is used to drive
  • the first preset time length corresponds to the longitudinal distance difference between the front and rear body of the vehicle;
  • the correction angle represents the angle change of the front and rear body of the vehicle in the current driving direction, and the first preset time period corresponds to the vehicle speed;
  • the lateral correction distance represents the current driving direction of the vehicle, and the lateral distance difference between the front and rear vehicle bodies corresponding to the first preset duration of driving at the vehicle speed;
  • the prediction value is determined based on the prediction data and the initial value of the coefficient to be processed.
  • the area prediction module is configured to:
  • the estimated time is determined based on the longitudinal distance and the vehicle speed of the own vehicle, and the initial value of the quadratic term coefficient is determined based on the curvature of the own vehicle and the estimated time; wherein, the estimated time is represented by the vehicle's curvature Vehicle speed, the time it takes for the vehicle to reach the location of the vehicle to be followed from its current location.
  • the area prediction module is configured to:
  • a lateral correction distance corresponding to the second vehicle parameter is determined based on the correction angle and the first preset time distance.
  • the region prediction module is configured to:
  • the longitudinal correction distance corresponding to the second vehicle parameter obtained based on each sampling is accumulated to obtain the longitudinal correction value; the correction angle corresponding to the second vehicle parameter obtained based on each sampling is accumulated to obtain the angle correction value; the angle correction value is obtained based on each sampling.
  • the lateral correction distance corresponding to the sampled second vehicle parameter is accumulated to obtain a lateral accumulation value;
  • the initial value of the quadratic term coefficient is used as the predicted value of the quadratic term coefficient.
  • the lane line information also includes a confidence indicating whether the sensor feedback lane line trajectory is accurate; performing the step of determining the lane line of the road section where the vehicle is located based on the feedback value and the predicted value. area, the target determination module is configured as:
  • the least squares method is used to perform a fitting operation on the feedback value and the predicted value, and the lane line area is determined according to the fitting operation result of the parameter item.
  • the target determination module is configured to determine whether to use the vehicle to be followed as a following target based on the lane line area and the location of the vehicle to be followed.
  • the driving information at least includes the speed, acceleration, heading angle and location of the vehicle to be followed;
  • the target determination module is configured to determine whether to use the vehicle to be followed as a following target based on the left and right boundaries of the vehicle body and the lane line area.
  • the vehicle to be followed is used as the following target; wherein the first distance represents the lateral distance from the center point of the vehicle to the left boundary of the vehicle body; The second distance represents the lateral distance from the center point of the vehicle to the left boundary of the lane line area;
  • the vehicle to be followed is used as the following target; where the third distance represents the lateral direction from the center point of the vehicle to the right boundary of the vehicle body. distance; the fourth distance represents the lateral distance from the center point of the vehicle to the right boundary of the lane line area;
  • the vehicle to be followed is used as the following target
  • the vehicle to be followed is used as the following target; wherein the first weight and the second weight are based on The confidence level is determined, and the first weight is greater than the second weight.
  • this application provides an electronic device, including:
  • Memory used to store program instructions
  • a processor configured to call program instructions stored in the memory, and execute the steps included in the method described in any one of the first aspects according to the obtained program instructions.
  • the present application provides a computer-readable storage medium that stores a computer program.
  • the computer program includes program instructions. When executed by a computer, the program instructions cause the computer to execute The method according to any one of the first aspects.
  • the application provides a computer program product.
  • the computer program product includes: computer program code.
  • the computer program code When the computer program code is run on a computer, it causes the computer to execute any one of the steps described in the first aspect. method.
  • Figure 1 is a schematic diagram of an application scenario provided by an embodiment of this application.
  • Figure 2 is an overall flow chart of a car following target determination method provided by an embodiment of the present application
  • Figure 3 is a schematic diagram of determining an accumulated value based on a second vehicle parameter provided by an embodiment of the present application
  • Figure 4 is a schematic diagram of the meaning of each accumulated value corresponding to the vehicle provided by the embodiment of the present application.
  • Figure 5 is a schematic diagram of the expansion of the lane line area provided by the embodiment of the present application.
  • Figure 6 is a schematic diagram of the correlation distance provided by the embodiment of the present application.
  • Figure 7 is a schematic diagram of the left and right boundaries of the vehicle body provided by the embodiment of the present application.
  • Figure 8 is a schematic diagram of distance comparison under the departure trend provided by the embodiment of the present application.
  • Figure 9 is another schematic diagram of distance comparison under the departure trend provided by the embodiment of the present application.
  • Figure 10 is a schematic diagram of distance comparison under the driving-in trend provided by the embodiment of the present application.
  • Figure 11 is another schematic diagram of distance comparison under the driving-in trend provided by the embodiment of the present application.
  • Figure 12 is a structural diagram of a vehicle following target determination device 1200 provided by an embodiment of the present application.
  • Figure 13 is a structural diagram of an electronic device provided by an embodiment of the present application.
  • the autonomous driving function is specifically divided into two driving modes: Traffic JamAssis (TJA) and Highway Assist (HWA) for different vehicle speeds.
  • the traffic jam assist function is mainly aimed at lateral counterweight control driving strategies in a lower speed range.
  • the lane lines of the road section where the vehicle is located are obtained through the image acquisition device to plan the vehicle's driving trajectory to ensure that the vehicle drives within the lane.
  • the confidence of the collected lane images will be low.
  • the image acquisition device cannot recognize the complete lane line trajectory.
  • the car-following mode means that in order to ensure stable driving while the vehicle is driving, the vehicle is controlled to follow the target vehicle's driving trajectory at the same speed as the vehicle-following target selected ahead.
  • the traditional car following method usually selects a motor vehicle from the front of the vehicle that meets the lateral distance from the vehicle to follow the trajectory of the motor vehicle and drive automatically.
  • the confidence of the lane image is low, it is impossible to determine whether the following target is in the same lane as the own vehicle based on the lateral distance alone, causing safety risks.
  • the inventive concept of the present application is to determine the feedback value of the parameter item by obtaining the lane line information fed back by the own vehicle sensor, and determine the predicted value of the parameter item based on the first vehicle parameter. Since the first vehicle parameters include the current vehicle speed, curvature, and longitudinal distance from the vehicle to be followed, the above predicted value represents the lane line area predicted based on the driving status of the vehicle to be followed and the vehicle. In addition, since the above feedback value represents the lane line area of the road section where the vehicle is located detected by the vehicle's sensor, the final lane line area can be comprehensively estimated based on the feedback value and the predicted value, and then by detecting whether the location of the vehicle to be followed is in the lane. within the line area to determine whether to use the vehicle to be followed as the following target.
  • Figure 1 is a schematic diagram of an application scenario according to an embodiment of the present application.
  • the application scenario may include, for example, a network 10 , a vehicle 20 , and a server 30 .
  • the vehicle 20 includes a variety of vehicles with automatic driving functions such as the car 20_1, the truck 20_2, and the passenger car 20_n shown in FIG. 1 .
  • the vehicle 20 activates the autonomous driving mode
  • the lane line trajectory fed back by the sensor is monitored in real time. If the confidence level of the lane line trajectory is low, the car following mode is enabled.
  • the server 30 selects a motor vehicle in front of the vehicle as the vehicle to be followed, and predicts the lane line prediction trajectory of the road section where the vehicle 20 is currently located based on the current speed of the vehicle 20, the curvature of the vehicle 20, and the longitudinal distance between the vehicle 20 and the vehicle to be followed.
  • the server 30 combines the confidence of the lane line trajectory fed back by the sensor to determine the trajectory prediction area based on the above lane line trajectory and the lane line prediction trajectory. If the vehicle to be followed is within the trajectory prediction area, the vehicle to be followed will be followed.
  • the confidence of the lane line trajectory fed back by the server 30 sensor determines the trajectory prediction area. Specifically, when the confidence level is high, the server 30 uses the lane line trajectory fed back by the sensor as the trajectory prediction area; when the confidence level is low, the server 30 uses the lane line prediction trajectory as the trajectory prediction area; when the confidence level is moderate, the server 30 30 The least squares method is used to fit the lane line prediction trajectory and the lane line trajectory fed back by the sensor to obtain the trajectory prediction area.
  • Step 201 In response to the car following instruction, obtain the lane line information and the first vehicle parameter fed back by the own vehicle's sensor; wherein the lane line information at least includes the feedback value of the parameter item characterizing the lane line trajectory; the first vehicle parameter At least including the own vehicle speed of the own vehicle, the curvature of the own vehicle, and the longitudinal distance between the vehicle to be followed and the own vehicle.
  • the vehicle to be followed is the vehicle located in front of the own vehicle selected by the sensor based on preset decision conditions;
  • the vehicle after the vehicle activates the car-following mode, it pre-selects the motor vehicle located in front of the vehicle as the vehicle to be followed based on preset decision-making conditions. Then obtain the lane line information and first vehicle parameters fed back by the sensor.
  • This lane line information represents the lane line trajectory of the road section where the vehicle is located determined by the vehicle sensor.
  • the constant coefficient C0 in the lane line trajectory equation represents the lateral distance between the vehicle and the lane line
  • C1 represents the heading angle of the lane line trajectory
  • C2 represents the curvature of the lane line trajectory
  • C3 represents the change rate of the curvature of the lane line trajectory
  • X represents the longitudinal distance
  • y represents the lateral distance.
  • the feedback values of the above parameter items are the values of C0 to C3 determined based on the lane line trajectory fed back by the sensor.
  • the range of the drivable lane should be narrowed with the vehicle as the center. That is, the constant term coefficients and linear term coefficients in the lane line trajectory equation should decrease as the vehicle speed increases to reduce the judgment range of the car following target.
  • the cubic term coefficient has a low impact on the prediction results of lane line trajectories and can be ignored. Due to traffic congestion or weather conditions, the sensor may not be able to completely and accurately identify the lane line trajectory. That is to say, the above feedback value cannot accurately represent the true trajectory of the lane line of the road condition where the vehicle is located.
  • this application sets the corresponding relationship between the first vehicle parameter and the parameter item based on a large amount of test data, so as to directly determine the predicted value of each parameter item based on the first vehicle parameter. That is, the sensor is disengaged, and the lane line trajectory of the road condition where the vehicle is located is predicted only through the first vehicle parameters. See the steps below for details.
  • Step 202 Determine the predicted value of the parameter item based on the first vehicle parameter, and determine the lane line area of the road section where the vehicle is located based on the feedback value and the predicted value;
  • the embodiment of the present application uses the preset cubic term calibration value as the predicted value of the cubic term coefficient.
  • the predicted value of the cubic term coefficient can be set to 0.
  • the initial value of the coefficient to be processed is determined according to the first vehicle parameter, and the coefficient to be processed is the constant term coefficient, linear term coefficient and quadratic term coefficient of the predicted value to be obtained.
  • the embodiment of the present application sets in advance the corresponding relationship between the vehicle speed and the initial value of the constant term and the initial value of the linear term based on a large amount of experimental data, as well as the corresponding relationship between the estimated time and the curvature coefficient. Specifically, after determining the vehicle speed, look up the table to obtain the initial value of the constant term and the initial value of the linear term corresponding to the preset speed interval where the vehicle's vehicle speed is located, and use the initial value of the constant term as the initial value of the coefficient of the constant term, and use the initial value of the linear term The initial value of the term is used as the initial value of the coefficient of the linear term.
  • the estimated time required for the vehicle to reach the location of the vehicle to be followed from the current position is determined using the vehicle speed of the vehicle. Since the larger the estimated time is, the farther the vehicle to be followed is from the own vehicle, the smaller the change rate of curvature should be. Therefore, after determining the estimated time, the curvature weight can be obtained by looking up the table.
  • C2 in the lane line trajectory formula represents the lane line curvature.
  • the specific value of the lane line curvature is 2C2 obtained by deriving the lane line trajectory formula. That is, the curvature of this car corresponds to the above 2C2.
  • the initial value needs to be corrected based on the actual driving situation of the vehicle to improve the prediction accuracy of the lane line area.
  • the second vehicle parameter of the vehicle may be sampled every first preset time period based on the preset sampling times.
  • the second vehicle parameters are determined based on the own vehicle sensors, including the own vehicle speed V and the yaw angular velocity Y of the own vehicle. Further, prediction data corresponding to the second vehicle parameter sampled this time is determined based on the second vehicle parameter obtained in each sampling. Then, the predicted value of each parameter to be processed is determined based on the predicted data and the initial value of the parameter to be processed.
  • the prediction data in the embodiment of the present application includes longitudinal correction distance, correction angle and lateral correction distance.
  • Figure 3 the total 50 sets of second vehicle parameters, each set of second vehicle parameters are V n and Y n , n is a positive integer not greater than 50.
  • the longitudinal correction distance d_s of this sampling is determined based on the vehicle speed V n and the sampling period T, and the correction angle corresponding to this sampling is determined based on the yaw angular velocity Y n and the sampling period T.
  • d_C1 determine the lateral correction distance d_C0 of this sampling based on the correction angle d_C1 and the longitudinal correction distance d_s obtained in this sampling.
  • the longitudinal correction distance d_s is the product of the vehicle speed V n and the first preset duration T, which represents the longitudinal distance difference of the vehicle body before and after the vehicle extends in the current driving direction and uses the vehicle speed to travel for the first preset duration corresponding to the duration.
  • the correction angle d_C1 is the product of the yaw angular velocity Y n and the first preset duration T, which represents the angle change of the front and rear body of the vehicle in the current driving direction and the first preset duration corresponding to the vehicle speed.
  • the lateral correction distance d_C0 is the product of the sine value of the correction angle d_C1 and the longitudinal correction distance d_s, which represents the lateral distance difference between the front and rear body of the vehicle in the current driving direction and the first preset duration corresponding to the vehicle speed.
  • the number 1 in Figure 4 is the current posture of the vehicle.
  • Label 2 is the vehicle position after the vehicle has traveled for the first preset time period T.
  • the angle between the solid line and the dotted line shown in Figure 4 is the correction angle d_C1.
  • the longitudinal distance between the vehicle postures labeled 1 and 2 is the above-mentioned longitudinal correction distance d_s
  • the lateral distance is the above-mentioned lateral correction distance d_C0.
  • correction angle d_C1 and lateral correction distance d_C0 for each sampling through the above process (a total of 50 d_s, d_C1 and d_C0). Accumulate the d_s obtained each time to obtain the sum of longitudinal correction distances dx within the sampling period. Accumulate the d_C1 obtained each time to obtain the sum of the correction angles dC1 of the sampling period. Correspondingly, d_C0 obtained each time is accumulated to obtain the sum of lateral correction distances dC0 within the sampling period.
  • C0_est is the initial value of the above-mentioned constant term coefficient
  • C1_est is the initial value of the above-mentioned linear term coefficient
  • C2_est is the initial value of the above-mentioned quadratic term coefficient
  • the quadratic term coefficient can be The initial value is directly used as the predicted value C2' of the quadratic term coefficient.
  • the lane line trajectory fed back by the vehicle's sensor is obtained through the above step 201, and then the feedback values C0 ⁇ C3 of the coefficients of each parameter term in the lane line trajectory equation are obtained.
  • the lane line trajectory predicted based on the vehicle parameters is obtained, and then the predicted values C3' ⁇ C3' of each parameter coefficient are obtained. Since the vehicle sensor will synchronize the confidence of the feedback trajectory when it feeds back the lane line trajectory, the confidence represents the credibility of the feedback result.
  • the lane line area is determined based on the feedback values C0 ⁇ C3 of the parameter items without reference to the predicted values C3' ⁇ C3. '.
  • the feedback result representing the sensor has a low reference value.
  • the lane line area can be determined based on the predicted values C3' ⁇ C3' of the parameter items without reference to the feedback values C0 ⁇ C3.
  • the confidence level when the confidence level is in the third confidence interval, it means that the feedback result of the sensor is closer to the real road condition, but the detected distance is smaller (for example, the detection distance End is less than 50 meters).
  • the least square method needs to be used for fitting based on the predicted values C3' ⁇ C3' and feedback values C0 ⁇ C3 of the parameter items to obtain the final lane line area.
  • the feedback values C0 ⁇ C3 and C3' ⁇ C3' can be respectively brought into the lane line trajectory equation to obtain the first lane line trajectory equation fed back by the sensor and the second lane line trajectory equation based on vehicle parameter prediction.
  • the above 10 points are fitted by the least squares method to obtain the final lane line trajectory equation, which corresponds to the final lane line area.
  • the above process means that the feedback value of the sensor is used to determine the lane line trajectory within the sensor detection range, and the predicted value is used to determine the remaining lane line trajectory for the part beyond the sensor detection range.
  • the driving information of the vehicle to be followed is first obtained based on the own vehicle's sensors.
  • the driving information includes the speed, acceleration, heading angle and location of the vehicle to be followed.
  • the predicted position of the vehicle to be followed relative to the own vehicle after traveling for the second preset time using the above driving information is determined through the following formula (2):
  • d0 is the position of the vehicle to be followed relative to the own vehicle
  • v is the speed of the vehicle to be followed relative to the own vehicle
  • a is the acceleration of the vehicle to be followed relative to the own vehicle
  • t is the second preset time.
  • d is the predicted position of the vehicle to be followed relative to the own vehicle after traveling for the second preset time through the above v and a;
  • substituting the driving information of the vehicle to be followed can obtain the posture of the vehicle to be followed after traveling along the current driving state for 0.5 seconds, that is, the predicted position of the vehicle to be followed after traveling for the second preset time period.
  • the purpose of determining the predicted position based on the driving information is to predict the posture of the vehicle to be followed after traveling a short distance based on the current driving state of the vehicle to be followed. Then, it is judged based on the posture whether the vehicle to be followed will leave or enter the lane line area.
  • Step 203 Determine whether to use the vehicle to be followed as a following target based on the lane line area and the location of the vehicle to be followed.
  • the lane marking area can be expanded based on the confidence level of the sensor feedback.
  • the vehicle to be followed has two tendencies: entering the lane marking area (Cutin) and leaving the lane marking area (Cutout). Based on these two trends, this application sets corresponding weights to expand the lane line area to determine whether to follow the vehicle based on the positional relationship between the left and right boundaries of the vehicle body at the predicted position and the expanded lane line area.
  • This target is the following target.
  • line 1 in Figure 5 is the left and right boundaries of the lane line area determined based on the above prediction value and feedback value.
  • Line 2 is a boundary line used to determine whether the vehicle to be followed is Cutout after expanding Line 1 based on the first weight.
  • line 3 is the boundary line used to determine whether the vehicle to be followed is Cutin after expanding line 1 based on the second weight.
  • the first weight needs to be controlled to be greater than the second weight. That is, the left boundary of the lane line area is expanded to the left by the lateral distance of the first weight to obtain the Cutout left boundary, and the right boundary of the lane line is expanded to the right by the lateral distance of the first weight to obtain the Cutout right boundary. Expand the left boundary of the lane line area to the left by the lateral distance of the second weight to obtain the Cutin left boundary, and expand the right boundary of the lane line to the right by the lateral distance of the second weight to obtain the Cutin right boundary.
  • the first weight representing Cutout can be set to 1.25, and the second weight representing Cutin can be set to 1.
  • the judgment range can be appropriately relaxed. Specifically, the first weight representing Cutout can be set to 1.5, and the second weight representing Cutin can be set to 1.2.
  • the center point of the vehicle can be used as the origin of the coordinate system to construct the vehicle coordinate system.
  • the lateral distance between the center point of the own vehicle and the left boundary of the vehicle body of the vehicle to be followed is the first distance.
  • the lateral distance between the center point of the vehicle and the left boundary of the lane line area is the second distance.
  • the lateral distance between the center point of the own vehicle and the right boundary of the vehicle body of the vehicle to be followed is the third distance.
  • the lateral area between the center point of the vehicle and the right boundary of the lane line area is the fourth distance.
  • the judgment process specifically includes the following four points:
  • the first point is to determine the position of the left boundary of the vehicle body to be followed and the left boundary line of Cutout;
  • the second point is to determine the position of the right boundary of the vehicle body to be followed and the right boundary line of Cutout;
  • the third point is to determine the position of the left boundary of the vehicle body to be followed and the left boundary line of Cutin;
  • the fourth point is to determine the position of the right boundary of the vehicle body to be followed and the right boundary line of Cutin.
  • Line 1 in Figure 8 is the left boundary of the lane line area
  • line 2 is the direction of line 1 based on the first weight. The left boundary line of Cutout obtained after left expansion.
  • the vehicle to be followed should not be used as the following target. That is, when the first distance is greater than or equal to the product of the second distance and the first weight, the body of the vehicle to be followed has exceeded the Cutout boundary line, and the vehicle to be followed is not used as the following target at this time.
  • Line 1 in Figure 9 is the right boundary of the lane line area
  • line 2 is the direction of line 1 based on the first weight.
  • the right boundary line of Cutout obtained after right expansion.
  • Line 1 in Figure 10 is the left boundary of the lane line area
  • line 3 is the direction of line 1 based on the second weight. The left boundary line of Cutin obtained after left expansion.
  • the vehicle to be followed can be used as the following target. That is, when the product of the second distance and the second weight is greater than the first distance, the vehicle to be followed can be used as the following target.
  • Line 1 in Figure 11 is the right boundary of the lane line area
  • line 3 is the direction of line 1 based on the second weight. Cutin boundary line obtained after right expansion.
  • the vehicle to be followed can be used as the following target. That is, when the product of the fourth distance and the second weight is greater than the third distance, the vehicle to be followed can be used as the following target.
  • the lane line area is predicted based on the confidence of the lane line trajectory recognized by the sensor and the lane line trajectory estimated based on the attitude of the vehicle. Then, it is determined whether the vehicle to be followed has left or entered the lane of the own vehicle at the predicted position by using the left and right boundaries of the vehicle body of the vehicle to be followed at the predicted position.
  • the embodiment of the present application provides a vehicle following target determination device 1200, as shown in Figure 12, including:
  • the parameter acquisition module 1201 is configured to obtain the lane line information and the first vehicle parameter fed back by the vehicle's sensor in response to the vehicle following instruction; wherein the lane line information at least includes feedback values of parameter items characterizing the lane line trajectory;
  • the first vehicle parameters at least include the own vehicle speed of the own vehicle, the curvature of the own vehicle, and the longitudinal distance between the vehicle to be followed and the own vehicle.
  • the vehicle to be followed is located in front of the own vehicle selected by the sensor based on preset decision conditions. Vehicles;
  • the area prediction module 1202 is configured to determine the predicted value of the parameter item based on the first vehicle parameter, and determine the lane line area of the road segment where the vehicle is located based on the feedback value and the predicted value;
  • the target determination module 1203 is configured to determine whether to use the vehicle to be followed as a following target based on the lane line area and the location of the vehicle to be followed.
  • the parameter term includes a constant term coefficient, a linear term coefficient, a quadratic term coefficient and a cubic term coefficient; performing the step of determining the predicted value of the parameter term based on the first vehicle parameter, so
  • the region prediction module 1202 is configured as:
  • the preset cubic term calibration value is used as the predicted value of the cubic term coefficient, and the initial value of the coefficient to be processed is determined according to the first vehicle parameter; wherein the coefficient to be processed includes the constant term coefficient, the The linear term coefficient and the quadratic term coefficient;
  • the second vehicle parameter of the vehicle is sampled every first preset time period; wherein the second vehicle parameter is determined based on the sensor of the vehicle, and the second vehicle parameter includes the vehicle's own Vehicle speed and yaw rate;
  • the prediction data is determined according to the second vehicle parameters; wherein the prediction data at least includes a longitudinal correction distance, a correction angle and a lateral correction distance; the longitudinal correction distance represents the current driving direction of the vehicle, and the speed of the vehicle is used to drive
  • the first preset time length corresponds to the longitudinal distance difference between the front and rear body of the vehicle;
  • the correction angle represents the angle change of the front and rear body of the vehicle in the current driving direction, and the first preset time period corresponds to the vehicle speed;
  • the lateral correction distance represents the current driving direction of the vehicle, and the lateral distance difference between the front and rear vehicle bodies corresponding to the first preset duration of driving at the vehicle speed;
  • the prediction value is determined based on the prediction data and the initial value of the coefficient to be processed.
  • the area prediction module 1202 is configured to:
  • the estimated time is determined based on the longitudinal distance and the vehicle speed of the own vehicle, and the initial value of the quadratic term coefficient is determined based on the curvature of the own vehicle and the estimated time; wherein, the estimated time is represented by the vehicle's curvature Vehicle speed, the time it takes for the vehicle to reach the location of the vehicle to be followed from its current location.
  • the area prediction module 1202 is configured to:
  • a lateral correction distance corresponding to the second vehicle parameter is determined based on the correction angle and the first preset time distance.
  • the region prediction module 1202 is configured to:
  • the longitudinal correction distance corresponding to the second vehicle parameter obtained based on each sampling is accumulated to obtain the longitudinal correction value; the correction angle corresponding to the second vehicle parameter obtained based on each sampling is accumulated to obtain the angle correction value; the angle correction value is obtained based on each sampling.
  • the lateral correction distance corresponding to the sampled second vehicle parameter is accumulated to obtain a lateral accumulation value;
  • the initial value of the quadratic term coefficient is used as the predicted value of the quadratic term coefficient.
  • the lane line information also includes a confidence indicating whether the sensor feedback lane line trajectory is accurate; performing the step of determining the lane line of the road section where the vehicle is located based on the feedback value and the predicted value.
  • the target determination module 1203 is configured as:
  • the least squares method is used to perform a fitting operation on the feedback value and the predicted value, and the lane line area is determined according to the fitting operation result of the parameter item.
  • the target determination module 1203 is configured to:
  • the driving information at least includes the speed, acceleration, heading angle and location of the vehicle to be followed;
  • the target determination module 1203 is configured to determine whether to use the vehicle to be followed as a following target based on the left and right boundaries of the vehicle body and the lane line area.
  • the vehicle to be followed is used as the following target; wherein the first distance represents the lateral distance from the center point of the vehicle to the left boundary of the vehicle body; The second distance represents the lateral distance from the center point of the vehicle to the left boundary of the lane line area;
  • the vehicle to be followed is used as the following target; where the third distance represents the lateral direction from the center point of the vehicle to the right boundary of the vehicle body. distance; the fourth distance represents the lateral distance from the center point of the vehicle to the right boundary of the lane line area;
  • the vehicle to be followed is used as the following target
  • the vehicle to be followed is used as the following target; wherein the first weight and the second weight are based on The confidence level is determined, and the first weight is greater than the second weight.
  • the electronic device 130 according to this embodiment of the present application is described below with reference to FIG. 13 .
  • the electronic device 130 shown in FIG. 13 is only an example and should not bring any limitations to the functions and usage scope of the embodiments of the present application.
  • the electronic device 130 is embodied in the form of a general electronic device.
  • the components of the electronic device 130 may include, but are not limited to: the above-mentioned at least one processor 131, the above-mentioned at least one memory 132, and a bus 133 connecting different system components (including the memory 132 and the processor 131).
  • Bus 133 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor, or a local bus using any of a variety of bus structures.
  • Memory 132 may include readable media in the form of volatile memory, such as random access memory (RAM) 1321 and/or cache memory 1322 , and may further include read only memory (ROM) 1323 .
  • RAM random access memory
  • ROM read only memory
  • Memory 132 may also include a program/utility 1325 having a set of (at least one) program modules 1324 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, which Each of the examples, or some combination thereof, may include the implementation of a network environment.
  • program/utility 1325 having a set of (at least one) program modules 1324 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, which Each of the examples, or some combination thereof, may include the implementation of a network environment.
  • Electronic device 130 may also communicate with one or more external devices 134 (e.g., keyboard, pointing device, etc.), may also communicate with one or more devices that enable a user to interact with electronic device 130, and/or with one or more devices that enable the electronic device 130 to 130 Any device (eg, router, modem, etc.) capable of communicating with one or more other electronic devices. This communication may occur through input/output (I/O) interface 135.
  • the electronic device 130 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through a network adapter 136. As shown, network adapter 136 communicates with other modules for electronic device 130 via bus 133 .
  • networks e.g., a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet
  • a computer-readable storage medium including instructions such as a memory 132 including instructions, which can be executed by the processor 131 of the device 1200 to complete the above method is also provided.
  • the computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
  • a computer program product including a computer program/instruction, which when executed by the processor 131 implements any one of the car following target determination methods provided by this application. method.
  • various aspects of a car following target determination method provided by this application can also be implemented in the form of a program product, which includes program code.
  • the program product is run on a computer device, the program code is The computer device is caused to execute the steps in the vehicle following target determination method described above in this specification according to various exemplary embodiments of the present application.
  • the Program Product may take the form of one or more readable media in any combination.
  • the readable medium may be a readable signal medium or a readable storage medium.
  • the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • the program product for car following target determination may adopt a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on an electronic device.
  • CD-ROM portable compact disk read-only memory
  • the program product of the present application is not limited thereto.
  • a readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus or device.
  • the readable signal medium may include a data signal propagated in baseband or as part of a carrier wave carrying readable program code therein. Such propagated data signals may take a variety of forms, including - but not limited to - electromagnetic signals, optical signals, or any suitable combination of the above.
  • a readable signal medium may also be any readable medium other than a readable storage medium that can send, propagate, or transport the program for use by or in connection with an instruction execution system, apparatus, or device.
  • Program code embodied on a readable medium may be transmitted using any suitable medium, including - but not limited to - wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
  • the program code for performing the operations of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., as well as conventional procedural programming. Language—such as Python or a similar programming language.
  • the program code may execute entirely on the user's electronic device, partly on the user's electronic device, as a stand-alone software package, partly on the user's electronic device and partly on a remote electronic device, or entirely on the remote electronic device or service Executed on the terminal.
  • the remote electronic devices may be connected to the user electronic device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external electronic device (e.g., using an Internet service). provider to connect via the Internet).
  • LAN local area network
  • WAN wide area network
  • Internet service e.g., using an Internet service
  • embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment that combines software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable image scaling device to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means, the instructions
  • the device implements the functions specified in a process or processes of the flowchart and/or a block or blocks of the block diagram.
  • These computer program instructions may also be loaded onto a computer or other programmable image scaling device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby executing on the computer or other programmable device.
  • Instructions provide steps for implementing the functions specified in a process or processes of a flowchart diagram and/or a block or blocks of a block diagram.

Landscapes

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

Abstract

本申请涉及汽车自动化技术领域，具体涉及一种跟车目标确定方法、装置、设备及介质。该方法包括：通过获取本车传感器反馈的车道线信息以确定参数项的反馈值，并根据第一车辆参数确定参数项的预测值。由于第一车辆参数包含本车当前车速、曲率以及与待跟随车辆的纵向距离，因而上述预测值表征了基于待跟随车辆与本车行驶状态预测的车道线区域。另由于上述反馈值表征了本车传感器检测的本车所在路段的车道线区域，可根据反馈值和预测值综合估算出最终的车道线区域，进而通过检测待跟随车辆的所在位置是否处于车道线区域内，以确定是否将待跟随车辆作为跟车目标。

Description

一种跟车目标确定方法、装置、设备及介质
相关申请的交叉引用
本申请要求在2022年04月19日提交中国专利局、申请号为202210408078.1、申请名称为“一种跟车目标确定方法、装置、设备及介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及汽车自动化技术领域，具体涉及一种跟车目标确定方法、装置、设备及介质。
背景技术
随着科技的发展，近年来的车辆多具备自动驾驶功能。通过该功能可保证在一定时间内驾驶员可以脱手脱脚驾驶。该功能主要通过图像采集装置获取本车所在路段的车道线，以对本车行驶轨迹进行规划，保证车辆在车道内行驶。上述控制方式主要依赖于图像采集装置捕捉的车道图像，当受天气影响或车道较为拥堵时会导致车道图像不清晰，置信度较低时，将会退出自动驾驶模式。
为避免因上述原因频繁退出自动驾驶模式，多通过启用跟车模式从本车前方选定处于与本车横向距离满足要求的机动车辆，以跟随该机动车辆的轨迹自动驾驶。然而，在车道图像置信度较低的情况下，仅根据横向距离无法确定跟车目标是否与本车处于同一车道，造成安全隐患。
发明内容
本申请实施例提供一种跟车目标确定方法、装置、设备及介质，用于确定跟车目标是否与本车处于相同车道。
第一方面，本申请实施例提供了一种跟车目标确定方法，所述方法包括：
响应于跟车指示，获取本车传感器反馈的车道线信息以及第一车辆参数；其中，所述车道线信息至少包括表征车道线轨迹的参数项的反馈值；所述第一车辆参数至少包括本车的本车车速、本车曲率以及待跟随车辆与本车的纵向距离，所述待跟随车辆为所述传感器基于预设决策条件选定的位于本车前方的车辆；
基于所述第一车辆参数确定所述参数项的预测值，并基于所述反馈值与所述预测值确定本车所在路段的车道线区域；
根据所述车道线区域和所述待跟随车辆的所在位置确定是否将所述待跟随车辆作为跟车目标。
本申请实施例通过获取本车传感器反馈的车道线信息以确定参数项的反馈值，并根据第一车辆参数确定参数项的预测值。由于第一车辆参数包含本车当前车速、曲率以及与待跟随车辆的纵向距离，因而上述预测值表征了基于待跟随车辆与本车行驶状态预测的车道线区域。另由于上述反馈值表征了本车传感器检测的本车所在路段的车道线区域，可根据反馈值和预测值综合估算出最终的车道线区域，进而通过检测根据待跟随车辆的所在位置是否处于车道线区域内，以确定是否将待跟随车辆作为跟车目标。
响应于跟车指示，获取本车传感器反馈的车道线信息以及第一车辆参数；其中，所述车道线信息至少包括表征车道线轨迹的参数项的反馈值；所述第一车辆参数至少包括本车的本车车速、本车曲率以及待跟随车辆与本车的纵向距离，所述待跟随车辆为所述传感器基于预设决策条件选定的位于本车前方的车辆；
基于所述第一车辆参数确定所述参数项的预测值，并基于所述反馈值与所述预测值确定本车所在路段的车道线区域；
根据所述车道线区域和所述待跟随车辆的所在位置确定是否将所述待跟随车辆作为跟车目标。
在一些可能的实施例中，所述参数项包括常数项系数、一次项系数、二次项系数以及三次项系数；所述基于所述第一车辆参数确定所述参数项的预 测值，包括：
将预设的三次项标定值作为所述三次项系数的预测值，并根据所述第一车辆参数确定待处理系数的初始值；其中，所述待处理系数包括所述常数项系数、所述一次项系数和所述二次项系数；
基于预设采样次数，每隔第一预设时长对本车的第二车辆参数进行采样；其中，所述第二车辆参数是基于本车传感器确定的，所述第二车辆参数包括本车的本车车速和横摆角速度；
根据所述第二车辆参数确定预测数据；其中，所述预测数据至少包括纵向修正距离、修正角度和横向修正距离；所述纵向修正距离表征本车延当前行驶方向，采用所述本车车速行驶所述第一预设时长对应时长前后的车身纵向距离差；所述修正角度表征本车延当前行驶方向，采用所述本车车速行驶所述第一预设时长对应时长前后车身的角度变化；所述横向修正距离表征本车延当前行驶方向，采用所述本车车速行驶所述第一预设时长对应时长前后车身横向距离差；
基于所述预测数据和所述待处理系数的初始值确定所述预测值。
本申请实施例中基于预设采样次数，每隔预设时间对本车的车速和横摆角速度进行采集，并根据每次采集后的本车车速和横摆角速度确定车道线轨迹方程中的各参数项的预测值，以提高对车道线轨迹区域的预测精度。
在一些可能的实施例中，所述根据所述第一车辆参数确定待处理系数的初始值，包括：
基于预设的车速对应关系，确定所述本车车速所在的预设速度区间对常数项初值和一次项初值；将所述常数项初值作为所述常数项系数的初始值，并将所述一次项初值作为所述一次项系数的初始值；
根据所述纵向距离和所述本车车速确定预计时间，并根据所述本车曲率和所述预计时间确定所述二次项系数的初始值；其中，所述预计时间表征采用所述本车车速行驶，本车从当前位置到达所述待跟随车辆所在位置所需的时间。
本申请实施例预设有不同速度区间对应的常数项初值和一次项初值，其原因在于，在车道线轨迹方程中常数项系数表征车道线轨迹与本车的横向距离、一次项系数表征车道线轨迹的航向角，这两个参数项均与本车车速负相关，故此可根据本车车速所在的预设速度区间确定常常数项系数的初始值和一次项系数的初始值。另由于二次项系数表征车道线轨迹的曲率，根据纵向距离与本车车速可得到延本车车速行驶，从本车当前位置到达待跟随车辆所在位置的预计时间，根据该预计时间与本车曲率即可确定三次项系数的初始值。
在一些可能的实施例中，所述根据所述第二车辆参数确定预测数据，包括：
针对每次采样得到的第二车辆参数，根据所述本车车速和所述第一预设时长确定所述第二车辆参数对应的纵向修正距离；
针对每次采样得到的第二车辆参数，根据所述横摆角速度和所述第一预设时长确定所述第二车辆参数对应的修正角度；
针对每次采样得到的第二车辆参数，根据所述修正角度和所述第一预设时长离确定所述第二车辆参数对应的横向修正距离。
本申请实施例中根据每次采样得到的第二车辆参数确定单次采样的纵向修正距离、修正角度以及横向修正距离。纵向修正距离表征延本车车速行驶，本车从当前位置到达待跟随车辆所在位置前后的车身纵向距离变化、修正角度表征延本车车速行驶，本车从当前位置到达待跟随车辆所在位置前后的车身角度变化、横向修正距离表征延本车车速行驶，本车从当前位置到达待跟随车辆所在位置前后的车身横向距离变化。通过这三个修正参数对表征车道线轨迹的参数项的初始值进行修正，以提高对车道线轨迹区域的预测精度。
在一些可能的实施例中，所述基于所述预测数据和所述待处理系数的初始值确定所述预测值，包括：
基于每次采样得到的第二车辆参数对应的纵向修正距离进行累加，得到纵向修正值；对基于每次采样得到的第二车辆参数对应的修正角度进行累加， 得到角度修正值；对基于每次采样得到的第二车辆参数对应的横向修正距离进行累加，得到横向累加值；
基于车道线轨迹方程，根据所述待处理系数的初始值、所述纵向累加值、所述横向累加值确定所述常数项系数的预测值和所述一次项系数的预测值；
将所述二次项系数的初始值作为所述二次项系数的预测值。
本申请实施例中将每次采样得到的修正参数进行累加。通过将各待处理系数的初始值作为车道线轨迹方程中对应参数项的值后，将修正参数带入方程，以获取常数项系数的预测值和一次项系数的预测值，另由于确定二次项系数初始值时，代入了本车与待跟随车辆的纵向距离，即已参考了本车所在的真实路况，因而可将二次项系数的初始值作为二次项系数的预测值。
在一些可能的实施例中，所述车道线信息还包括表征所述传感器反馈车道线轨迹是否准确的置信度；所述基于所述反馈值与所述预测值确定本车所在路段的车道线区域，包括：
若所述置信度处于第一置信度区间，则根据所述参数项的反馈值确定所述车道线区域；
若所述置信度处于第二置信度区间，则根据所述参数项的预测值确定所述车道线区域；
若所述置信度处于第三置信度区间，则采用最小二乘法对所述反馈值和所述预测值进行拟合运算，并根据所述参数项的拟合运算结果确定所述车道线区域。
本申请实施例在置信度较高时，选用传感器反馈的参数项确定车道线区域，在置信度较低时，选用参数项的预测值确定车道线区域。并在置信度适中时，通过最小二乘法对参数项的反馈值和预测值进行拟合，以得到综合传感器反馈结果和基于车辆参数预测结果得到的最终的车道线区域，由此提高车道线轨迹的预测精度。
在一些可能的实施例中，所述根据所述车道线区域和所述待跟随车辆的所在位置确定是否将所述待跟随车辆作为跟车目标，包括：
根据本车传感器获取所述待跟随车辆的行驶信息；其中，所述行驶信息至少包括所述待跟随车辆的车速、加速度、航向角以及所在位置；
确定所述待跟随车辆延所述行驶信息行驶第二预设时长后的预测位置，并确定所述待跟随车辆行驶至所述预测位置时所述待跟随车辆的车体左边界和车体右边界；
根据所述车体左边界、所述车体右边界和所述车道线区域确定是否将所述待跟随车辆作为跟车目标。
本申请实施例根据待跟随车辆当前的行驶信息确定待跟随车辆即将行驶的轨迹，由此可确定待跟随车辆是否驶离车道线区域。当待跟随车辆将驶离车道线区域时表征待跟随车辆与本车不处于同一车道线，此时不应将待跟随车辆作为跟车目标。
在一些可能的实施例中，所述根据所述车体左右边界和所述车道线区域确定是否将所述待跟随车辆作为跟车目标，包括：
若第二距离与第一权重之积大于第一距离，则将所述待跟随车辆作为所述跟车目标；其中，所述第一距离表征本车中心点到达车体左边界的横向距离；所述第二距离表征本车中心点到达所述车道线区域的左边界的横向距离；
若第四距离与所述第一权重之积大于第三距离，则将所述待跟随车辆作为所述跟车目标；其中，所述第三距离表征本车中心点到达车体右边界的横向距离；所述第四距离表征本车中心点到达所述车道线区域的右边界的横向距离；
若所述第二距离与第二权重之积大于所述第一距离，则将所述待跟随车辆作为所述跟车目标；
若所述第四距离与所述第二权重之积大于所述第三距离，则将所述待跟随车辆作为所述跟车目标；其中，所述第一权重和所述第二权重是根据所述置信度确定的，且所述第一权重大于所述第二权重。
本申请实施例根据置信度的不同设有对应的权重。由此可根据本车与车道线左右边界的横向距离以及本车与待跟随车辆左右边界的横向距离的比对 结果，确定待跟随车辆是否要驶离车道线区域，由此可避免选定的跟车目标与本车不处于同一车道线。
第二方面，本申请实施例提供了一种跟车目标确定装置，所述装置包括：
参数获取模块，被配置为执行响应于跟车指示，获取本车传感器反馈的车道线信息以及第一车辆参数；其中，所述车道线信息至少包括表征车道线轨迹的参数项的反馈值；所述第一车辆参数至少包括本车的本车车速、本车曲率以及待跟随车辆与本车的纵向距离，所述待跟随车辆为所述传感器基于预设决策条件选定的位于本车前方的车辆；
区域预测模块，被配置为执行基于所述第一车辆参数确定所述参数项的预测值，并基于所述反馈值与所述预测值确定本车所在路段的车道线区域；
目标判定模块，被配置为执行根据所述车道线区域和所述待跟随车辆的所在位置确定是否将所述待跟随车辆作为跟车目标。
在一些可能的实施例中，所述参数项包括常数项系数、一次项系数、二次项系数以及三次项系数；执行所述基于所述第一车辆参数确定所述参数项的预测值，所述区域预测模块被配置为：
将预设的三次项标定值作为所述三次项系数的预测值，并根据所述第一车辆参数确定待处理系数的初始值；其中，所述待处理系数包括所述常数项系数、所述一次项系数和所述二次项系数；
基于预设采样次数，每隔第一预设时长对本车的第二车辆参数进行采样；其中，所述第二车辆参数是基于本车传感器确定的，所述第二车辆参数包括本车的本车车速和横摆角速度；
根据所述第二车辆参数确定预测数据；其中，所述预测数据至少包括纵向修正距离、修正角度和横向修正距离；所述纵向修正距离表征本车延当前行驶方向，采用所述本车车速行驶所述第一预设时长对应时长前后的车身纵向距离差；所述修正角度表征本车延当前行驶方向，采用所述本车车速行驶所述第一预设时长对应时长前后车身的角度变化；所述横向修正距离表征本车延当前行驶方向，采用所述本车车速行驶所述第一预设时长对应时长前后 车身横向距离差；
基于所述预测数据和所述待处理系数的初始值确定所述预测值。
在一些可能的实施例中，执行所述根据所述第一车辆参数确定待处理系数的初始值，所述区域预测模块被配置为：
基于预设的车速对应关系，确定所述本车车速所在的预设速度区间对常数项初值和一次项初值；将所述常数项初值作为所述常数项系数的初始值，并将所述一次项初值作为所述一次项系数的初始值；
根据所述纵向距离和所述本车车速确定预计时间，并根据所述本车曲率和所述预计时间确定所述二次项系数的初始值；其中，所述预计时间表征采用所述本车车速行驶，本车从当前位置到达所述待跟随车辆所在位置所需的时间。
在一些可能的实施例中，执行所述根据所述第二车辆参数确定预测数据，所述区域预测模块被配置为：
针对每次采样得到的第二车辆参数，根据所述本车车速和所述第一预设时长确定所述第二车辆参数对应的纵向修正距离；
针对每次采样得到的第二车辆参数，根据所述横摆角速度和所述第一预设时长确定所述第二车辆参数对应的修正角度；
针对每次采样得到的第二车辆参数，根据所述修正角度和所述第一预设时长离确定所述第二车辆参数对应的横向修正距离。
在一些可能的实施例中，执行所述基于所述预测数据和所述待处理系数的初始值确定所述预测值，所述区域预测模块被配置为：
基于每次采样得到的第二车辆参数对应的纵向修正距离进行累加，得到纵向修正值；对基于每次采样得到的第二车辆参数对应的修正角度进行累加，得到角度修正值；对基于每次采样得到的第二车辆参数对应的横向修正距离进行累加，得到横向累加值；
基于车道线轨迹方程，根据所述待处理系数的初始值、所述纵向累加值、所述横向累加值确定所述常数项系数的预测值和所述一次项系数的预测值；
将所述二次项系数的初始值作为所述二次项系数的预测值。
在一些可能的实施例中，所述车道线信息还包括表征所述传感器反馈车道线轨迹是否准确的置信度；执行所述基于所述反馈值与所述预测值确定本车所在路段的车道线区域，所述目标判定模块被配置为：
若所述置信度处于第一置信度区间，则根据所述参数项的反馈值确定所述车道线区域；
若所述置信度处于第二置信度区间，则根据所述参数项的预测值确定所述车道线区域；
若所述置信度处于第三置信度区间，则采用最小二乘法对所述反馈值和所述预测值进行拟合运算，并根据所述参数项的拟合运算结果确定所述车道线区域。
在一些可能的实施例中，执行所述根据所述车道线区域和所述待跟随车辆的所在位置确定是否将所述待跟随车辆作为跟车目标，所述目标判定模块被配置为：
根据本车传感器获取所述待跟随车辆的行驶信息；其中，所述行驶信息至少包括所述待跟随车辆的车速、加速度、航向角以及所在位置；
确定所述待跟随车辆延所述行驶信息行驶第二预设时长后的预测位置，并确定所述待跟随车辆行驶至所述预测位置时所述待跟随车辆的车体左边界和车体右边界；
根据所述车体左边界、所述车体右边界和所述车道线区域确定是否将所述待跟随车辆作为跟车目标。
在一些可能的实施例中，执行所述根据所述车体左右边界和所述车道线区域确定是否将所述待跟随车辆作为跟车目标，所述目标判定模块被配置为：
若第二距离与第一权重之积大于第一距离，则将所述待跟随车辆作为所述跟车目标；其中，所述第一距离表征本车中心点到达车体左边界的横向距离；所述第二距离表征本车中心点到达所述车道线区域的左边界的横向距离；
若第四距离与所述第一权重之积大于第三距离，则将所述待跟随车辆作 为所述跟车目标；其中，所述第三距离表征本车中心点到达车体右边界的横向距离；所述第四距离表征本车中心点到达所述车道线区域的右边界的横向距离；
若所述第二距离与第二权重之积大于所述第一距离，则将所述待跟随车辆作为所述跟车目标；
若所述第四距离与所述第二权重之积大于所述第三距离，则将所述待跟随车辆作为所述跟车目标；其中，所述第一权重和所述第二权重是根据所述置信度确定的，且所述第一权重大于所述第二权重。
第三方面，本申请提供一种电子设备，包括：
存储器，用于存储程序指令；
处理器，用于调用所述存储器中存储的程序指令，按照获得的程序指令执行第一方面中任一项所述的方法包括的步骤。
第四方面，本申请提供一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被计算机执行时，使所述计算机执行第一方面中任一项所述的方法。
第五方面，本申请提供了一种计算机程序产品，所述计算机程序产品包括：计算机程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行第一方面中任一项所述的方法。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对本申请实施例中所需要使用的附图作简单地介绍，显而易见地，下面所介绍的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的应用场景示意图；
图2为本申请实施例提供的一种跟车目标确定方法整体流程图；
图3为本申请实施例提供的基于第二车辆参数确定累加值示意图；
图4为本申请实施例提供的各累加值对应车辆含义示意图；
图5为本申请实施例提供的对车道线区域扩充示意图；
图6为本申请实施例提供的相关距离示意图；
图7为本申请实施例提供的车体左右边界示意图；
图8为本申请实施例提供的驶离趋势下的距离比对示意图；
图9为本申请实施例提供的驶离趋势下的距离比对的另一示意图；
图10为本申请实施例提供的驶入趋势下的距离比对示意图；
图11为本申请实施例提供的驶入趋势下的距离比对的另一示意图；
图12为本申请实施例提供的一种跟车目标确定装置1200结构图；
图13为本申请实施例提供的一种电子设备的结构图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚明白，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互任意组合。并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以按不同于此处的顺序执行所示出或描述的步骤。
本申请的说明书和权利要求书及上述附图中的术语“第一”和“第二”是用于区别不同对象，而非用于描述特定顺序。此外，术语“包括”以及它们任何变形，意图在于覆盖不排他的保护。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。本申请中的“多个”可以表示至少两个，例如可以是两个、三个或者更多，本申请实施例不做限制。
本申请技术方案中，对数据的采集、传播、使用等，均符合国家相关法律法规要求。
自动驾驶功能针对不同车速，具体划分为交通拥堵辅助(Traffic JamAssis，TJA)和高速驾驶辅助(Highway Assist，HWA)两种驾驶模式。交通拥堵辅助功能主要针对车速在较低范围内的横向对重控制行驶策略。具体通过图像采集装置获取本车所在路段的车道线，以对本车行驶轨迹进行规划，保证车辆在车道内行驶。然而车道较为拥堵或受如大雾、大雨等导致视线较差的天气影响时，会使采集的车道图像置信度较低，此时图像采集装置无法识别到完整的车道线轨迹。
为在该条件下实现自动驾驶需启用跟车模式。跟车模式即为车辆行驶过程中为保证稳定行驶，控制本车以与前方选定的跟车目标相同车速跟随目标车辆的行驶轨迹自动行驶。传统的跟车方式多从本车前方选定处于与本车横向距离满足要求的机动车辆，以跟随该机动车辆的轨迹自动驾驶。然而，在车道图像置信度较低的情况下，仅根据横向距离无法确定跟车目标是否与本车处于同一车道，造成安全隐患。
为解决上述问题，本申请的发明构思为：通过获取本车传感器反馈的车道线信息以确定参数项的反馈值，并根据第一车辆参数确定参数项的预测值。由于第一车辆参数包含本车当前车速、曲率以及与待跟随车辆的纵向距离，因而上述预测值表征了基于待跟随车辆与本车行驶状态预测的车道线区域。另由于上述反馈值表征了本车传感器检测的本车所在路段的车道线区域，因而可根据反馈值和预测值综合估算出最终的车道线区域，进而通过检测待跟随车辆的所在位置是否处于车道线区域内，以确定是否将待跟随车辆作为跟车目标。
参见图1，为根据本申请一个实施例的应用场景示意图。
如图1所示，该应用场景中例如可以包括网络10、车辆20以及服务器30。其中：车辆20包括图1中示出的轿车20_1、货车20_2以及客车20_n等多种具备自动驾驶功能的车辆。
在图1示出的应用场景中，车辆20启用自动驾驶模式后，实时监测传感器反馈的车道线轨迹。若车道线轨迹的置信度较低时则启用跟车模式。
服务器30从本车前方选定一机动车辆作为待跟随车辆，根据车辆20的当前车速、车辆20的曲率以及车辆20与待跟随车辆的纵向距离预测车辆20当前所在路段的车道线预测轨迹。服务器30结合传感器反馈的车道线轨迹的置信度，根据上述车道线轨迹和车道线预测轨迹确定轨迹预测区域。若待跟随车辆处于该轨迹预测区域内，则跟随待跟随车辆行驶。
在一些可能的实施例中，服务器30传感器反馈的车道线轨迹的置信度确定轨迹预测区域。具体的，当置信度较高时，服务器30将传感器反馈的车道线轨迹作为轨迹预测区域；当置信度较低时，服务器30将车道线预测轨迹作为轨迹预测区域；当置信度适中时，服务器30采用最小二乘法对车道线预测轨迹和传感器反馈的车道线轨迹进行拟合以得到轨迹预测区域。
需要说明的是，本申请中的描述中仅就单个服务器或智能设备加以详述，但是本领域技术人员应当理解的是，图1示出的服务器30旨在表示本申请的技术方案涉及的服务器的操作。对单个服务器加以详述至少为了说明方便，而非暗示对服务器的数量、类型或是位置等具有限制。应当注意，如果向图示环境中添加附加模块或从其中去除个别模块，不会改变本申请的示例实施例的底层概念。
介绍了本申请技术方案的应用场景后，下面结合附图对本申请实施例提供的一种车辆出行方法进行详细说明，具体如图2所示，包括下述步骤：
步骤201：响应于跟车指示，获取本车传感器反馈的车道线信息以及第一车辆参数；其中，所述车道线信息至少包括表征车道线轨迹的参数项的反馈值；所述第一车辆参数至少包括本车的本车车速、本车曲率以及待跟随车辆与本车的纵向距离，所述待跟随车辆为所述传感器基于预设决策条件选定的位于本车前方的车辆；
本申请实施例中，车辆启用跟车模式后预先基于预设决策条件选定位于本车前方的机动车辆作为待跟随车辆。然后获取传感器反馈的车道线信息和 第一车辆参数。该车道线信息表征车传感器确定的本车所在路段的车道线轨迹。该车道线轨迹可由车道线轨迹方程y＝C0+C1X+C2X 2+C3X 3进行表示。其中，车道线轨迹方程中的常数项系数C0表征本车与车道线横向距离、C1表征车道线轨迹的航向角、C2表征车道线轨迹的曲率、C3表征车道线轨迹曲率的变化率。X表征纵向距离、y表征横向距离。
应理解的是，上述参数项的反馈值即为根据传感器反馈的车道线轨迹确定的C0～C3的值。
为保证车辆行驶的安全性，当车速较高时，应以本车为中心，收缩可行驶车道的范围。即车道线轨迹方程中的常数项系数与一次项系数均应随车速增加而减少，以减小跟车目标的判断范围。此外，三次项系数对车道线轨迹的预测结果影响较低，可以忽略。由于路况拥堵或受天气原因影响，会导致传感器无法完整、准确的识别车道线轨迹。即上述反馈值并不能准确表征本车所在路况的车道线真实轨迹。
基于此，本申请基于大量试验数据设定第一车辆参数与参数项的对应关系，以直接基于第一车辆参数确定各参数项的预测值。即脱离传感器，仅通过第一车辆参数对本车所在路况的车道线轨迹进行预测。具体参见下述步骤。
步骤202：基于所述第一车辆参数确定所述参数项的预测值，并基于所述反馈值与所述预测值确定本车所在路段的车道线区域；
前文已提及，三次项系数对车道线轨迹的预测结果影响可以忽略。因而本申请实施例将预设的三次项标定值作为三次项系数的预测值。具体可将三次项系数的预测值设为0。进一步的，根据第一车辆参数确定待处理系数的初始值，待处理系数即为待求取预测值的常数项系数、一次项系数和二次项系数。
实施时，本申请实施例预先基于大量实验数据设定本车车速与常数项初值和一次项初值的对应关系，以及预计时间与曲率系数的对应关系。具体的，确定本车车速后，查表得到本车车速所在的预设速度区间对应的常数项初值和一次项初值，并将常数项初值作为常数项系数的初始值，并将一次项初值 作为一次项系数的初始值。
进一步的，根据纵向距离和本车车速确定表征采用本车车速行驶，本车从当前位置到达待跟随车辆所在位置所需的预计时间。由于预计时间越大表征待跟随车辆距离本车越远，曲率的变化率应越小。因此可在确定预计时间后，查表得到曲率权重。此外，前文已提及车道线轨迹公式中的C2表征车道线曲率，车道线曲率的具体数值为过对车道线轨迹公式进行求导后得到的2C2。即本车曲率对应上述2C2。因而根据本车曲率估算车道线轨迹方程中二次项系数的初始值时，需将本车曲率与曲率权重之积的一半作为二次项系数的初始值。
通过上述流程获取待处理系数的初始值后，需基于车辆行驶的实际情况对初始值进行修正，以提高车道线区域的预测精度。
实施时，可基于预设采样次数，每隔第一预设时长对本车的第二车辆参数进行采样。第二车辆参数是基于本车传感器确定的，包括本车的本车车速V和横摆角速度Y。进一步的，根据每次采样得到的第二车辆参数确定本次采样的第二车辆参数对应的预测数据。进而根据预测数据和待处理参数的初始值确定各待处理参数的预测值。
本申请实施例中的预测数据包括纵向修正距离、修正角度和横向修正距离。为便于说明如何根据预测数据和待处理参数的初始值确定各待处理参数的预测值。下面以0.02秒采样一次(即第一预设时长为0.02s)，共计采样50次为例(即采样周期为0.02s×50＝1s)进行说明，具体参见图3，该采样周期内共计得到50组第二车辆参数，每组第二车辆参数为V n和Y n，n为不大于50的正整数。针对每次采样得到的第二车辆参数，根据本车车速V n和采样周期T确定本次采样的纵向修正距离d_s，并根据横摆角速度Y n和采样周期T确定本次采样对应的修正角度d_C1，根据本次采样得到修正角度d_C1和纵向修正距离d_s确定本次采样的横向修正距离d_C0。
其中，纵向修正距离d_s为本车车速V n与第一预设时长T之积，表征本车延当前行驶方向，采用本车车速行驶第一预设时长对应时长前后的车身纵 向距离差。修正角度d_C1为横摆角速度Y n与第一预设时长T之积，表征本车延当前行驶方向，采用本车车速行驶第一预设时长对应时长前后车身的角度变化。横向修正距离d_C0则为修正角度d_C1的正弦值与纵向修正距离d_s之积，表征本车延当前行驶方向，采用本车车速行驶第一预设时长对应时长前后车身横向距离差。具体如图4所示，图4中的标号1为本车当前位姿。标号2为本车行驶第一预设时长T后的车辆位姿。图4中示出的实线与虚线间的夹角即为修正角度d_C1。标号1和标号2的车辆位姿纵向距离即为上述纵向修正距离d_s，横向距离即为上述横向修正距离d_C0。
通过上述流程获取每次采样的纵向修正距离d_s、修正角度d_C1以及横向修正距离d_C0后(共计50个d_s、d_C1以及d_C0)。将每次得到的d_s进行累加，得到采样周期内的纵向修正距离之和dx。将每次得到的d_C1累加，得到采样周期的修正角度之和dC1。相应的，将每次得到的d_C0累加，得到采样周期内的横向修正距离之和dC0。
将各参数项的初始值作为车道线轨迹方程，得到下述公式(1)中待求解的车道线轨迹方程：
y 1＝C0_est+C1_estX+C2_estX 2+C3_estX+C3'  (1)
其中，C0_est为上述常数项系数的初始值；C1_est为上述一次项系数的初始值；C2_est为上述二次项系数的初始值；C3'为预先标定的三次项系数的预测值，本申请中C3'＝0。
前文已提及，车道线轨迹方程中的未知数X表征纵向距离，因而可将上述dx作为未知数X带入上式(1)中，所得结果即为本车相距车道线的横向距离y 1。另由于采样周期内本车行驶前后横向距离变化了dC0。所以，用上述横向距离y 1减去dC0即为本车在采样周期内移动后与车道线轨迹的横向距离，即常数项系数的预测值C0'。
相应的，将上式(1)求导得到y 1'＝C1_est+2C2_estX；将dx带入该式可得到dx处的车道线的方向角度y 1'。另由于采样周期内本车行驶前后车体偏移了dC1。所以，用上述y 1'减去dC1后即为一次项系数的预测值C1'，表征dx 处车道线的航向角。
此外，由于上述确定二次项系数的初始值时，代入了本车与待跟随车辆的纵向距离，即已参考了本车所在的真实路况，因而该值无需修正，可将二次项系数的初始值直接作为二次项系数的预测值C2'。
综上，通过上述步骤201获取了本车传感器反馈的车道线轨迹，进而得到车道线轨迹方程中各参数项系数的反馈值C0～C3。通过上述步骤202得到了基于车辆参数预测的车道线轨迹，进而得到各参数项系数的预测值C3'～C3'。由于车辆传感器反馈车道线轨迹时会同步所反馈轨迹的置信度，该置信度表征反馈结果的可信程度。
本申请实施例中，当置信度处于第一置信度区间时表征传感器的反馈结果较为接近真实路况，此时根据参数项的反馈值C0～C3确定车道线区域，无需借鉴预测值C3'～C3'。相应的，当置信度处于第二置信度区间时表征传感器的反馈结果参考价值较低，此时可根据参数项的预测值C3'～C3'确定车道线区域，无需借鉴反馈值C0～C3。此外，当置信度处于第三置信度区间时表征传感器的反馈结果较为接近真实路况，但所探测的距离较小(例如探测距离End小于50米)。此时需根据参数项的预测值C3'～C3'和反馈值C0～C3，采用最小二乘法拟合以得到最终的车道线区域。
具体的，可分别将反馈值C0～C3和C3'～C3'带入车道线轨迹方程，以得到传感器反馈的第一车道线轨迹方程以及基于车辆参数预测的第二车道线轨迹方程。接下来，在第一车道线轨迹方程的[0，End]上均匀取点5个，并在第二车道线方程的[End，50]均匀取点5个。然后将上述10个点进行最小二乘法拟合出最终的车道线轨迹方程，该方程对应最终的车道线区域。上述流程即表征在传感器探测范围内选用传感器的反馈值确定车道线轨迹，超出传感器探测范围的部分则选用预测值确定余下车道线轨迹。
通过上述流程确定车道线区域后，需根据车道线区域和待跟随车辆的所在位置确定是否将待跟随车辆作为跟车目标。实施时，首先根据本车传感器获取待跟随车辆的行驶信息，行驶信息包括待跟随车辆的车速、加速度、航 向角以及所在位置。具体通过下述公式(2)确定待跟随车辆在采用上述行驶信息行驶第二预设时间后相对于本车的预测位置：
d＝d0+vt+0.5at 2  (2)
其中，d0为待跟随车辆相对于本车的位置；v为待跟随车辆相对于本车的速度；a为待跟随车辆相对于本车的加速度；t为第二预设时间。d为待跟随车辆通过上述v和a行驶第二预设时间后相对于本车的预测位置；
获取上述式(2)后，代入待跟随车辆的行驶信息即可获知待跟随车辆沿当前行驶状态行驶0.5s后的位姿，即待跟随车辆行驶第二预设时长后的预测位置。需要说明的是，上述根据行驶信息确定预测位置的目的在于基于待跟随车辆的当前行驶状态，预测待跟随车辆行驶一小段距离后的位姿。进而根据该位姿判断待跟随车辆是否将会驶离或驶入车道线区域。
步骤203：根据所述车道线区域和所述待跟随车辆的所在位置确定是否将所述待跟随车辆作为跟车目标。
考虑到上述车道线区域是通过估算方式得到的，并不能完全等同于真实路况。因而可基于传感器反馈的置信度为车道线区域进行扩充。待跟随车辆存在驶入车道线区域(Cutin)和驶离车道线区域(Cutout)两种趋势。本申请基于这两种趋势设置了对应的权重，用于对车道线区域进行扩充，以根据待跟随车辆在预测位置处的车体左右边界与扩充后的车道线区域的位置关系确定是否将待跟随车辆作为跟车目标。
如图5所示，图5中的线1即为基于上述预测值和反馈值确定的车道线区域的左右边界。线2为基于第一权重对线1进行扩充后，用于判断待跟随车辆是否Cutout的边界线。相应的，线3为基于第二权重对线1进行扩充后，用于判断待跟随车辆是否Cutin的边界线。为提高判断精度，需控制第一权重大于第二权重。即，将车道线区域左边界向左扩充第一权重的横向距离得到Cutout左边界，将车道线右边界向右扩充第一权重的横向距离得到Cutout右边界。将车道线区域左边界向左扩充第二权重的横向距离得到Cutin左边界，将车道线右边界向右扩充第二权重的横向距离得到Cutin右边界。
实施时，当本车传感器反馈的置信度较高时，可将表征Cutout的第一权重设置为1.25，并将表征Cutin的第二权重设置为1。当置信度较低时，可适当放宽判断范围，具体可将表征Cutout的第一权重设置为1.5，并将表征Cutin的第二权重设置为1.2。
应理解的是，跟车模式需确定跟车目标与本车处于相同车道。因而可将本车中心点作为坐标系原点，构建车辆坐标系。具体如图6所示，本车中心点与待跟随车辆的车体左边界的横向距离为第一距离。本车中心点与车道线区域左边界的横向距离为第二距离。本车中心点与待跟随车辆的车体右边界的横向距离为第三距离。本车中心点与车道线区域右边界的横向区域为第四距离。
另需说明的是，实际应用中的传感器采集的前车图像多为后视图，因而待跟随车辆的车体左右边界具体应如图7所示，其车体左右边界表示为待跟随车辆后视图中的车体左右截面。
根据待跟随车辆在预测位置处的车体左右边界与扩充后的车道线区域的位置关系确定是否将待跟随车辆作为跟车目标时，其判断流程具体包括下述四点：
第一点，待跟随车辆的车体左边界与Cutout左边界线的位置判断；
第二点，待跟随车辆的车体右边界与Cutout右边界线的位置判断；
第三点，待跟随车辆的车体左边界与Cutin左边界线的位置判断；
第四点，待跟随车辆的车体右边界与Cutin右边界线的位置判断。
针对第一点，待跟随车辆的车体左边界与Cutout左边界线的位置判断具体参见图8，图8中的线1为车道线区域的左边界，线2为根据第一权重对线1向左扩充后得到的Cutout左边界线。
如图8所示，当待跟随车辆的车体左边界处于线2左侧时，表征待跟随车辆驶离本车所在车道，此时不应将待跟随车辆作为跟车目标。即，第一距离大于或等于第二距离与第一权重之积时，待跟随车辆的车体已超出Cutout边界线，此时不将待跟随车辆作为跟车目标。
针对第二点，待跟随车辆的车体右边界与Cutout右边界线的位置判断具体参见图9，图9中的线1为车道线区域的右边界，线2为根据第一权重对线1向右扩充后得到的Cutout右边界线。
如图9所示，当待跟随车辆的车体右边界处于线2右侧时，表征待跟随车辆驶离本车所在车道，此时不应将待跟随车辆作为跟车目标。即，第三距离大于或等于第四距离与第一权重之积时，待跟随车辆的车体已超出Cutout边界线，此时不将待跟随车辆作为跟车目标。
针对第三点，待跟随车辆的车体左边界与Cutin左边界线的位置判断具体参见图10，图10中的线1为车道线区域的左边界，线3为根据第二权重对线1向左扩充后得到的Cutin左边界线。
如图10所示，当待跟随车辆的车体左边界处于线3右侧时，表征待跟随车辆驶入本车所在车道，此时可将待跟随车辆作为跟车目标。即，第二距离与第二权重之积大于第一距离时，可将待跟随车辆作为跟车目标。
针对第四点，待跟随车辆的车体右边界与Cutin右边界线的位置判断具体参见图11，图11中的线1为车道线区域的右边界，线3为根据第二权重对线1向右扩充后得到的Cutin边界线。
如图11所示，当待跟随车辆的车体右边界处于线3左侧时，表征待跟随车辆驶入本车所在车道，此时可将待跟随车辆作为跟车目标。即，第四距离与第二权重之积大于第三距离时，可将待跟随车辆作为跟车目标。
上述流程中基于传感器识别的车道线轨迹的置信度，根据传感器识别的车道线轨迹以及根据本车姿态估算的车道线轨迹预测出车道线区域。进而通过对待跟随车辆在预测位置处的车体左右边界确定待跟随车辆是否在预测位置处驶离或驶入了本车所在车道。
基于相同的发明构思，本申请实施例提供了一种跟车目标确定装置1200，如图12所示，包括：
参数获取模块1201，被配置为执行响应于跟车指示，获取本车传感器反馈的车道线信息以及第一车辆参数；其中，所述车道线信息至少包括表征车 道线轨迹的参数项的反馈值；所述第一车辆参数至少包括本车的本车车速、本车曲率以及待跟随车辆与本车的纵向距离，所述待跟随车辆为所述传感器基于预设决策条件选定的位于本车前方的车辆；
区域预测模块1202，被配置为执行基于所述第一车辆参数确定所述参数项的预测值，并基于所述反馈值与所述预测值确定本车所在路段的车道线区域；
目标判定模块1203，被配置为执行根据所述车道线区域和所述待跟随车辆的所在位置确定是否将所述待跟随车辆作为跟车目标。
在一些可能的实施例中，所述参数项包括常数项系数、一次项系数、二次项系数以及三次项系数；执行所述基于所述第一车辆参数确定所述参数项的预测值，所述区域预测模块1202被配置为：
将预设的三次项标定值作为所述三次项系数的预测值，并根据所述第一车辆参数确定待处理系数的初始值；其中，所述待处理系数包括所述常数项系数、所述一次项系数和所述二次项系数；
基于预设采样次数，每隔第一预设时长对本车的第二车辆参数进行采样；其中，所述第二车辆参数是基于本车传感器确定的，所述第二车辆参数包括本车的本车车速和横摆角速度；
根据所述第二车辆参数确定预测数据；其中，所述预测数据至少包括纵向修正距离、修正角度和横向修正距离；所述纵向修正距离表征本车延当前行驶方向，采用所述本车车速行驶所述第一预设时长对应时长前后的车身纵向距离差；所述修正角度表征本车延当前行驶方向，采用所述本车车速行驶所述第一预设时长对应时长前后车身的角度变化；所述横向修正距离表征本车延当前行驶方向，采用所述本车车速行驶所述第一预设时长对应时长前后车身横向距离差；
基于所述预测数据和所述待处理系数的初始值确定所述预测值。
在一些可能的实施例中，执行所述根据所述第一车辆参数确定待处理系数的初始值，所述区域预测模块1202被配置为：
基于预设的车速对应关系，确定所述本车车速所在的预设速度区间对常数项初值和一次项初值；将所述常数项初值作为所述常数项系数的初始值，并将所述一次项初值作为所述一次项系数的初始值；
根据所述纵向距离和所述本车车速确定预计时间，并根据所述本车曲率和所述预计时间确定所述二次项系数的初始值；其中，所述预计时间表征采用所述本车车速行驶，本车从当前位置到达所述待跟随车辆所在位置所需的时间。
在一些可能的实施例中，执行所述根据所述第二车辆参数确定预测数据，所述区域预测模块1202被配置为：
针对每次采样得到的第二车辆参数，根据所述本车车速和所述第一预设时长确定所述第二车辆参数对应的纵向修正距离；
针对每次采样得到的第二车辆参数，根据所述横摆角速度和所述第一预设时长确定所述第二车辆参数对应的修正角度；
针对每次采样得到的第二车辆参数，根据所述修正角度和所述第一预设时长离确定所述第二车辆参数对应的横向修正距离。
在一些可能的实施例中，执行所述基于所述预测数据和所述待处理系数的初始值确定所述预测值，所述区域预测模块1202被配置为：
基于每次采样得到的第二车辆参数对应的纵向修正距离进行累加，得到纵向修正值；对基于每次采样得到的第二车辆参数对应的修正角度进行累加，得到角度修正值；对基于每次采样得到的第二车辆参数对应的横向修正距离进行累加，得到横向累加值；
基于车道线轨迹方程，根据所述待处理系数的初始值、所述纵向累加值、所述横向累加值确定所述常数项系数的预测值和所述一次项系数的预测值；
将所述二次项系数的初始值作为所述二次项系数的预测值。
在一些可能的实施例中，所述车道线信息还包括表征所述传感器反馈车道线轨迹是否准确的置信度；执行所述基于所述反馈值与所述预测值确定本车所在路段的车道线区域，所述目标判定模块1203被配置为：
若所述置信度处于第一置信度区间，则根据所述参数项的反馈值确定所述车道线区域；
若所述置信度处于第二置信度区间，则根据所述参数项的预测值确定所述车道线区域；
若所述置信度处于第三置信度区间，则采用最小二乘法对所述反馈值和所述预测值进行拟合运算，并根据所述参数项的拟合运算结果确定所述车道线区域。
在一些可能的实施例中，执行所述根据所述车道线区域和所述待跟随车辆的所在位置确定是否将所述待跟随车辆作为跟车目标，所述目标判定模块1203被配置为：
根据本车传感器获取所述待跟随车辆的行驶信息；其中，所述行驶信息至少包括所述待跟随车辆的车速、加速度、航向角以及所在位置；
确定所述待跟随车辆延所述行驶信息行驶第二预设时长后的预测位置，并确定所述待跟随车辆行驶至所述预测位置时所述待跟随车辆的车体左边界和车体右边界；
根据所述车体左边界、所述车体右边界和所述车道线区域确定是否将所述待跟随车辆作为跟车目标。
在一些可能的实施例中，执行所述根据所述车体左右边界和所述车道线区域确定是否将所述待跟随车辆作为跟车目标，所述目标判定模块1203被配置为：
若第二距离与第一权重之积大于第一距离，则将所述待跟随车辆作为所述跟车目标；其中，所述第一距离表征本车中心点到达车体左边界的横向距离；所述第二距离表征本车中心点到达所述车道线区域的左边界的横向距离；
若第四距离与所述第一权重之积大于第三距离，则将所述待跟随车辆作为所述跟车目标；其中，所述第三距离表征本车中心点到达车体右边界的横向距离；所述第四距离表征本车中心点到达所述车道线区域的右边界的横向距离；
若所述第二距离与第二权重之积大于所述第一距离，则将所述待跟随车辆作为所述跟车目标；
若所述第四距离与所述第二权重之积大于所述第三距离，则将所述待跟随车辆作为所述跟车目标；其中，所述第一权重和所述第二权重是根据所述置信度确定的，且所述第一权重大于所述第二权重。
下面参照图13来描述根据本申请的这种实施方式的电子设备130。图13显示的电子设备130仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。
如图13所示，电子设备130以通用电子设备的形式表现。电子设备130的组件可以包括但不限于：上述至少一个处理器131、上述至少一个存储器132、连接不同系统组件(包括存储器132和处理器131)的总线133。
总线133表示几类总线结构中的一种或多种，包括存储器总线或者存储器控制器、外围总线、处理器或者使用多种总线结构中的任意总线结构的局域总线。
存储器132可以包括易失性存储器形式的可读介质，例如随机存取存储器(RAM)1321和/或高速缓存存储器1322，还可以进一步包括只读存储器(ROM)1323。
存储器132还可以包括具有一组(至少一个)程序模块1324的程序/实用工具1325，这样的程序模块1324包括但不限于：操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。
电子设备130也可以与一个或多个外部设备134(例如键盘、指向设备等)通信，还可与一个或者多个使得用户能与电子设备130交互的设备通信，和/或与使得该电子设备130能与一个或多个其它电子设备进行通信的任何设备(例如路由器、调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口135进行。并且，电子设备130还可以通过网络适配器136与一个或者多个网络(例如局域网(LAN)，广域网(WAN)和/或公共网络，例如因特 网)通信。如图所示，网络适配器136通过总线133与用于电子设备130的其它模块通信。应当理解，尽管图中未示出，可以结合电子设备130使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理器、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储系统等。
在示例性实施例中，还提供了一种包括指令的计算机可读存储介质，例如包括指令的存储器132，上述指令可由装置1200的处理器131执行以完成上述方法。可选地，计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
在示例性实施例中，还提供一种计算机程序产品，包括计算机程序/指令，所述计算机程序/指令被处理器131执行时实现如本申请提供的一种跟车目标确定方法中的任一方法。
在示例性实施例中，本申请提供的一种跟车目标确定方法的各个方面还可以实现为一种程序产品的形式，其包括程序代码，当程序产品在计算机设备上运行时，程序代码用于使计算机设备执行本说明书上述描述的根据本申请各种示例性实施方式的一种跟车目标确定方法中的步骤。
程序产品可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
本申请的实施方式的用于跟车目标确定的程序产品可以采用便携式紧凑盘只读存储器(CD-ROM)并包括程序代码，并可以在电子设备上运行。然而，本申请的程序产品不限于此，在本文件中，可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者 与其结合使用。
可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了可读程序代码。这种传播的数据信号可以采用多种形式，包括——但不限于——电磁信号、光信号或上述的任意合适的组合。可读信号介质还可以是可读存储介质以外的任何可读介质，该可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
可读介质上包含的程序代码可以用任何适当的介质传输，包括——但不限于——无线、有线、光缆、RF等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言的任意组合来编写用于执行本申请操作的程序代码，程序设计语言包括面向对象的程序设计语言—诸如Java、C++等，还包括常规的过程式程序设计语言—诸如语言或类似的程序设计语言。程序代码可以完全地在用户电子设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户电子设备上部分在远程电子设备上执行、或者完全在远程电子设备或服务端上执行。在涉及远程电子设备的情形中，远程电子设备可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户电子设备，或者，可以连接到外部电子设备(例如利用因特网服务提供商来通过因特网连接)。
应当注意，尽管在上文详细描述中提及了装置的若干单元或子单元，但是这种划分仅仅是示例性的并非强制性的。实际上，根据本申请的实施方式，上文描述的两个或更多单元的特征和功能可以在一个单元中具体化。反之，上文描述的一个单元的特征和功能可以进一步划分为由多个单元来具体化。
此外，尽管在附图中以特定顺序描述了本申请方法的操作，但是，这并非要求或者暗示必须按照该特定顺序来执行这些操作，或是必须执行全部所示的操作才能实现期望的结果。附加地或备选地，可以省略某些步骤，将多个步骤合并为一个步骤执行，和/或将一个步骤分解为多个步骤执行。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、 或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程图像缩放设备的处理器以产生一个机器，使得通过计算机或其他可编程图像缩放设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程图像缩放设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程图像缩放设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本申请的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例做出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本申请范围的所有变更和修改。
显然，本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的精神和范围。这样，倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。

Claims (11)

  1. 一种跟车目标确定方法，所述方法包括：
    响应于跟车指示，获取本车传感器反馈的车道线信息以及第一车辆参数；其中，所述车道线信息至少包括表征车道线轨迹的参数项的反馈值；所述第一车辆参数至少包括本车的本车车速、本车曲率以及待跟随车辆与本车的纵向距离，所述待跟随车辆为所述传感器基于预设决策条件选定的位于本车前方的车辆；
    基于所述第一车辆参数确定所述参数项的预测值，并基于所述反馈值与所述预测值确定本车所在路段的车道线区域；
    根据所述车道线区域和所述待跟随车辆的所在位置确定是否将所述待跟随车辆作为跟车目标。
  2. 根据权利要求1所述的方法，所述参数项包括常数项系数、一次项系数、二次项系数以及三次项系数；所述基于所述第一车辆参数确定所述参数项的预测值，包括：
    将预设的三次项标定值作为所述三次项系数的预测值，并根据所述第一车辆参数确定待处理系数的初始值；其中，所述待处理系数包括所述常数项系数、所述一次项系数和所述二次项系数；
    基于预设采样次数，每隔第一预设时长对本车的第二车辆参数进行采样；其中，所述第二车辆参数是基于本车传感器确定的，所述第二车辆参数包括本车的本车车速和横摆角速度；
    根据所述第二车辆参数确定预测数据；其中，所述预测数据至少包括纵向修正距离、修正角度和横向修正距离；所述纵向修正距离表征本车延当前行驶方向，采用所述本车车速行驶所述第一预设时长对应时长前后的车身纵向距离差；所述修正角度表征本车延当前行驶方向，采用所述本车车速行驶所述第一预设时长对应时长前后车身的角度变化；所述横向修正距离表征本车延当前行驶方向，采用所述本车车速行驶所述第一预设时长对应时长前后 车身横向距离差；
    基于所述预测数据和所述待处理系数的初始值确定所述预测值。
  3. 根据权利要求2所述的方法，所述根据所述第一车辆参数确定待处理系数的初始值，包括：
    基于预设的车速对应关系，确定所述本车车速所在的预设速度区间对常数项初值和一次项初值；将所述常数项初值作为所述常数项系数的初始值，并将所述一次项初值作为所述一次项系数的初始值；
    根据所述纵向距离和所述本车车速确定预计时间，并根据所述本车曲率和所述预计时间确定所述二次项系数的初始值；其中，所述预计时间表征采用所述本车车速行驶，本车从当前位置到达所述待跟随车辆所在位置所需的时间。
  4. 根据权利要求2所述的方法，所述根据所述第二车辆参数确定预测数据，包括：
    针对每次采样得到的第二车辆参数，根据所述本车车速和所述第一预设时长确定所述第二车辆参数对应的纵向修正距离；
    针对每次采样得到的第二车辆参数，根据所述横摆角速度和所述第一预设时长确定所述第二车辆参数对应的修正角度；
    针对每次采样得到的第二车辆参数，根据所述修正角度和所述第一预设时长离确定所述第二车辆参数对应的横向修正距离。
  5. 根据权利要求4所述的方法，所述基于所述预测数据和所述待处理系数的初始值确定所述预测值，包括：
    基于每次采样得到的第二车辆参数对应的纵向修正距离进行累加，得到纵向修正值；对基于每次采样得到的第二车辆参数对应的修正角度进行累加，得到角度修正值；对基于每次采样得到的第二车辆参数对应的横向修正距离进行累加，得到横向累加值；
    基于车道线轨迹方程，根据所述待处理系数的初始值、所述纵向累加值、所述横向累加值确定所述常数项系数的预测值和所述一次项系数的预测值；
    将所述二次项系数的初始值作为所述二次项系数的预测值。
  6. 根据权利要求1所述的方法，所述车道线信息还包括表征所述传感器反馈车道线轨迹是否准确的置信度；所述基于所述反馈值与所述预测值确定本车所在路段的车道线区域，包括：
    若所述置信度处于第一置信度区间，则根据所述参数项的反馈值确定所述车道线区域；
    若所述置信度处于第二置信度区间，则根据所述参数项的预测值确定所述车道线区域；
    若所述置信度处于第三置信度区间，则采用最小二乘法对所述反馈值和所述预测值进行拟合运算，并根据所述参数项的拟合运算结果确定所述车道线区域。
  7. 根据权利要求6所述的方法，所述根据所述车道线区域和所述待跟随车辆的所在位置确定是否将所述待跟随车辆作为跟车目标，包括：
    根据本车传感器获取所述待跟随车辆的行驶信息；其中，所述行驶信息至少包括所述待跟随车辆的车速、加速度、航向角以及所在位置；
    确定所述待跟随车辆延所述行驶信息行驶第二预设时长后的预测位置，并确定所述待跟随车辆行驶至所述预测位置时所述待跟随车辆的车体左边界和车体右边界；
    根据所述车体左边界、所述车体右边界和所述车道线区域确定是否将所述待跟随车辆作为跟车目标。
  8. 根据权利要求7所述的方法，所述根据所述车体左右边界和所述车道线区域确定是否将所述待跟随车辆作为跟车目标，包括：
    若第二距离与第一权重之积大于第一距离，则将所述待跟随车辆作为所述跟车目标；其中，所述第一距离表征本车中心点到达车体左边界的横向距离；所述第二距离表征本车中心点到达所述车道线区域的左边界的横向距离；
    若第四距离与所述第一权重之积大于第三距离，则将所述待跟随车辆作为所述跟车目标；其中，所述第三距离表征本车中心点到达车体右边界的横 向距离；所述第四距离表征本车中心点到达所述车道线区域的右边界的横向距离；
    若所述第二距离与第二权重之积大于所述第一距离，则将所述待跟随车辆作为所述跟车目标；
    若所述第四距离与所述第二权重之积大于所述第三距离，则将所述待跟随车辆作为所述跟车目标；其中，所述第一权重和所述第二权重是根据所述置信度确定的，且所述第一权重大于所述第二权重。
  9. 一种跟车目标确定装置，所述装置包括：
    参数获取模块，被配置为执行响应于跟车指示，获取本车传感器反馈的车道线信息以及第一车辆参数；其中，所述车道线信息至少包括表征车道线轨迹的参数项的反馈值；所述第一车辆参数至少包括本车的本车车速、本车曲率以及待跟随车辆与本车的纵向距离，所述待跟随车辆为所述传感器基于预设决策条件选定的位于本车前方的车辆；
    区域预测模块，被配置为执行基于所述第一车辆参数确定所述参数项的预测值，并基于所述反馈值与所述预测值确定本车所在路段的车道线区域；
    目标判定模块，被配置为执行根据所述车道线区域和所述待跟随车辆的所在位置确定是否将所述待跟随车辆作为跟车目标。
  10. 一种电子设备，包括：
    存储器，用于存储程序指令；
    处理器，用于调用所述存储器中存储的程序指令，按照获得的程序指令执行权利要求1-8中任一项所述的方法包括的步骤。
  11. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被计算机执行时，使所述计算机执行如权利要求1-8中任一项所述的方法。
PCT/CN2022/117116 2022-04-19 2022-09-05 一种跟车目标确定方法、装置、设备及介质 WO2023201964A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210408078.1 2022-04-19
CN202210408078.1A CN114750759B (zh) 2022-04-19 2022-04-19 一种跟车目标确定方法、装置、设备及介质

Publications (1)

Publication Number Publication Date
WO2023201964A1 true WO2023201964A1 (zh) 2023-10-26

Family

ID=82331412

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/117116 WO2023201964A1 (zh) 2022-04-19 2022-09-05 一种跟车目标确定方法、装置、设备及介质

Country Status (2)

Country Link
CN (1) CN114750759B (zh)
WO (1) WO2023201964A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117746362A (zh) * 2023-12-05 2024-03-22 北京卓视智通科技有限责任公司 一种车辆连续变道检测方法、系统、存储介质和电子设备
CN118182493A (zh) * 2024-03-15 2024-06-14 大连理工大学 智能网联环境下基于加速度反馈的车辆跟驰模型构建方法
CN118205551A (zh) * 2024-05-22 2024-06-18 中国第一汽车股份有限公司 自适应巡航车速控制方法、装置、车辆、介质及产品
US12080079B2 (en) * 2021-02-09 2024-09-03 Hyundai Mobis Co., Ltd. Lane recognition apparatus and method controlling same

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114750759B (zh) * 2022-04-19 2024-04-30 合众新能源汽车股份有限公司 一种跟车目标确定方法、装置、设备及介质
CN115320589B (zh) * 2022-10-13 2023-02-10 青岛慧拓智能机器有限公司 跟车速度规划方法、装置、芯片、终端、电子设备及介质
CN115320592B (zh) * 2022-10-13 2023-02-10 青岛慧拓智能机器有限公司 车速规划方法、装置、芯片、终端、计算机设备及介质
CN116682095B (zh) * 2023-08-02 2023-11-07 天津所托瑞安汽车科技有限公司 一种关注目标的确定方法、装置、设备及存储介质
CN117864172B (zh) * 2024-03-13 2024-05-31 吉咖智能机器人有限公司 一种自动驾驶控制方法、装置以及设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110803163A (zh) * 2018-07-19 2020-02-18 广州小鹏汽车科技有限公司 车辆行驶轨迹的预测、车辆跟随目标的选择方法及设备
CN112215209A (zh) * 2020-11-13 2021-01-12 中国第一汽车股份有限公司 跟车目标确定方法、装置、车辆及存储介质
WO2021195955A1 (zh) * 2020-03-31 2021-10-07 华为技术有限公司 检测车辆行驶场景的复杂度的方法和装置
WO2021259000A1 (zh) * 2020-06-24 2021-12-30 中国第一汽车股份有限公司 跟车控制方法、装置、车辆及存储介质
CN114750759A (zh) * 2022-04-19 2022-07-15 合众新能源汽车有限公司 一种跟车目标确定方法、装置、设备及介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6414524B2 (ja) * 2015-08-28 2018-10-31 株式会社デンソー 車両制御装置、及び走路信頼度判定方法
CN109409202B (zh) * 2018-09-06 2022-06-24 惠州市德赛西威汽车电子股份有限公司 基于动态感兴趣区域的鲁棒性车道线检测方法
CN113168708B (zh) * 2020-04-28 2022-07-12 华为技术有限公司 车道线跟踪方法和装置
CN113353078A (zh) * 2021-06-24 2021-09-07 中汽创智科技有限公司 一种无车道线自动跟车轨迹确定方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110803163A (zh) * 2018-07-19 2020-02-18 广州小鹏汽车科技有限公司 车辆行驶轨迹的预测、车辆跟随目标的选择方法及设备
WO2021195955A1 (zh) * 2020-03-31 2021-10-07 华为技术有限公司 检测车辆行驶场景的复杂度的方法和装置
WO2021259000A1 (zh) * 2020-06-24 2021-12-30 中国第一汽车股份有限公司 跟车控制方法、装置、车辆及存储介质
CN112215209A (zh) * 2020-11-13 2021-01-12 中国第一汽车股份有限公司 跟车目标确定方法、装置、车辆及存储介质
CN114750759A (zh) * 2022-04-19 2022-07-15 合众新能源汽车有限公司 一种跟车目标确定方法、装置、设备及介质

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12080079B2 (en) * 2021-02-09 2024-09-03 Hyundai Mobis Co., Ltd. Lane recognition apparatus and method controlling same
CN117746362A (zh) * 2023-12-05 2024-03-22 北京卓视智通科技有限责任公司 一种车辆连续变道检测方法、系统、存储介质和电子设备
CN118182493A (zh) * 2024-03-15 2024-06-14 大连理工大学 智能网联环境下基于加速度反馈的车辆跟驰模型构建方法
CN118205551A (zh) * 2024-05-22 2024-06-18 中国第一汽车股份有限公司 自适应巡航车速控制方法、装置、车辆、介质及产品

Also Published As

Publication number Publication date
CN114750759B (zh) 2024-04-30
CN114750759A (zh) 2022-07-15

Similar Documents

Publication Publication Date Title
WO2023201964A1 (zh) 一种跟车目标确定方法、装置、设备及介质
JP6845894B2 (ja) 自動運転車両におけるセンサー故障を処理するための方法
JP6892464B2 (ja) 自動運転車両に用いられる検知支援
JP7141370B2 (ja) 標準的なナビゲーション地図と車両の過去の軌跡に基づいて決定された車線構成を利用した自動運転
US11117569B2 (en) Planning parking trajectory generation for self-driving vehicles using optimization method
US20200331476A1 (en) Automatic lane change with minimum gap distance
US10488205B2 (en) Method and system for updating maps based on control feedbacks of autonomous driving vehicles
US10824153B2 (en) Cost design for path selection in autonomous driving technology
JP7108583B2 (ja) 自動運転車両のための曲率補正経路サンプリングシステム
EP3659004B1 (en) Drifting correction between planning stage and controlling stage of operating autonomous driving vehicles
JP6779326B2 (ja) 複数のスレッドを使用して自動運転車両に用いられる基準線を生成するための方法及びシステム
US10272778B2 (en) Method and system for determining unit gain of speed control for autonomous driving vehicles
US20180330173A1 (en) Speed control and steering control assistant based on pitch status and roll status of autonomous driving vehicle
US20200233420A1 (en) Method to define safe drivable area for automated driving system
US20180143632A1 (en) Method for determining command delays of autonomous vehicles
CN113335276A (zh) 障碍物的轨迹预测方法、装置、电子设备及存储介质
US11016489B2 (en) Method to dynamically determine vehicle effective sensor coverage for autonomous driving application
JP2020521191A (ja) 自動運転車両の高速道路における自動運転に用いる、地図及びポジショニングなしで車線に沿う走行方法
JP6908674B2 (ja) 自動運転車両を動作させるための所定のキャリブレーションテーブルに基づく車両制御システム
CN113050618B (zh) 用于操作自动驾驶车辆的计算机实现的方法
CN113537362A (zh) 一种基于车路协同的感知融合方法、装置、设备及介质
KR20190100855A (ko) 자율 주행 차량을 위한 자기 위치 측정 방법, 시스템 및 기계 판독 가능한 매체
JP2021511998A (ja) 自動運転車両のための螺旋曲線に基づく垂直駐車計画システム
WO2020164090A1 (en) Trajectory prediction for driving strategy
CN111707258B (zh) 一种外部车辆监测方法、装置、设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22938189

Country of ref document: EP

Kind code of ref document: A1